audit-code-complexity
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code, repository instructions, and configuration files that could contain malicious instructions designed to bypass agent constraints or manipulate output.
- Ingestion points: The skill reads target source code, callers, tests, repository configuration, and documentation as specified in
SKILL.md. - Boundary markers: No explicit boundary markers or delimiters are defined to isolate external data from instructions.
- Capability inventory: The agent has the ability to execute shell commands (e.g.,
git log) and perform file-system write operations to apply code refactors. - Sanitization: No sanitization or validation of the ingested external content is mentioned.
- [COMMAND_EXECUTION]: The skill utilizes shell commands for repository analysis.
- Evidence:
SKILL.mddirects the agent to "Usegit logto see which files change most often" during the audit process.
Audit Metadata