audit-context-building
Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.
- 0
- Installs
- —
- Rating
- —
- Success rate
- 5
- Files scanned
Do not let an agent install this unattended
Security scan
FlaggedHigh-risk patterns found. A human should read the source before any agent installs this.
- criticalHidden unicode characters (U+200B)
resources/ANALYSIS_FORMAT.md:25
⟦U+200B⟧```language
Invisible or direction-changing characters can hide instructions from human reviewers while the agent still reads them (TrapDoor / Trojan Source).
- criticalHidden unicode characters (U+200B)
resources/ANALYSIS_FORMAT.md:28
⟦U+200B⟧```
Invisible or direction-changing characters can hide instructions from human reviewers while the agent still reads them (TrapDoor / Trojan Source).
Content sha256 1f80109c720318f4… — run codexguild_scan_skills after installing to verify your local copy.
Static analysis is a first line of defense, not a guarantee. Read the source
SKILL.md
Audit Context Building
Build understanding, not verdicts. This runs before anyone hunts for bugs, and feeds that work.
When to Use
At the start of an audit, a threat model, or an architecture review, when the code is unfamiliar. Also when an earlier pass produced findings nobody could judge, because no one had mapped out how the system fits together.
When NOT to Use
Do not name vulnerabilities, suggest fixes, write proofs-of-concept, or rate severity. Those belong to the hunting phase, which runs next and with the whole picture in hand. When the code counts on something and nothing checks it, record that plainly and move on — whether it matters is decided later.
Not worth the tokens on code you already understand.
Do not analyze in this context
The analysis is long, and this context needs to survive to use it. Dispatch it:
- A codebase, or more than one function — run
/audit-context-building:audit-context <path>. It orients, analyzes each function in its own subagent, and writesaudit-context/DOSSIER.mdplus one file per function underaudit-context/functions/. Only compact records return here. - A single function — dispatch the
audit-context-building:function-analyzeragent at it. It writes its prose to disk and returns a record.
Then work from what comes back: the index, the unenforced assumptions, the open questions. Read a function's file when you need its detail.
The workflow is what enforces this, not this text: a subagent bound to a return schema cannot return prose. Treat this section as routing, and route.
What comes back, and how to read it
Each record lists what must always be true (with the line that shows it), what the function takes on faith (with whatever establishes it), which functions it calls and what it needs from each, and anything still unclear. The dossier adds the rules that span several functions, who can reach what, and where the complicated parts cluster.
Two things matter more than the rest:
- Assumptions marked
nothing found. The code counts on something being true and nothing anywhere makes it true. This is the most useful thing to hand the hunting phase. - The open questions. An honest list of what is still unclear beats a confident answer that turns out to be wrong. Carry them forward instead of closing them out.
Where two records disagree, both are quoted rather than quietly reconciled. That is a fact about the code, not a flaw in the analysis.
The format
ANALYSIS_FORMAT.md defines it, and FUNCTION_MICRO_ANALYSIS_EXAMPLE.md works through examples in C and Solidity. Read them when extending this plugin or deciding whether a record can be trusted.
The format is the same whatever the target. What changes is what fills each slot, and what counts as a call you cannot see inside. DOMAIN_NOTES.md maps that across smart contracts, C and C++, decompiled firmware, and web services — read it when the target is not plain source code.
The rule that matters most: follow the calls. Whether a function is correct usually depends on something
another function does, and you cannot see that from the caller alone. A limit looks enforced because the
value came back from a function whose name suggests it was checked. So read the function being called, follow
every path through it rather than only the one that succeeds, and say what makes each assumption true. When
nothing does, use those words: nothing found. Every claim cites a line, or becomes an open question.
Files
5- SKILL.md
33fa693dc63.9 KB - agents/openai.yaml
1d66ff830f253 B - resources/ANALYSIS_FORMAT.md
02953294572.6 KB - resources/DOMAIN_NOTES.md
ca3090f7f84.9 KB - resources/FUNCTION_MICRO_ANALYSIS_EXAMPLE.md
3351010d838.8 KB
Agent reviews
0No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.
More from trailofbits/skills8
Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=address builds, ASAN_OPTIONS, reading the crash report, LeakSanitizer, and the overhead and platform trade-offs. Use when fuzzing C/C++ or Rust th
Sets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and secondary campaigns, persistent mode, corpus minimization, and crash triage. Use when scaling fuzzing across cores, fuzzing a mature C/C++ codeba
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary p
Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL/PyTeal).
Sets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure Python and native C extensions, and running under AddressSanitizer. Use when fuzzing a Python package, hunting memory corruption in a Python C ex
Augments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x binary-analysis graph exports. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-refere
Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments). Use when preparing your own codebase
Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.
Related security skillsscan passed
AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component interactions, and catching vulnerabilities that pattern-matching tools miss. Use this skill when asked to scan code for security vulnerabilities, find bugs, check for
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppS
Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings. Use when hunting reportable, remotely reachable vulnerabilities in a repository.
Security audit: supported static findings; qualified profiles add reproduction and repair candidates. (gstack)
Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose). Use when the use
Implement JWT/cookie authentication and authorization in tRPC using createContext for user extraction, t.middleware with opts.next({ ctx }) for context narrowing to non-null user, protectedProcedure base pattern, client-side Authorization headers via httpBatchLink headers(), WebSocket connectionPara