componentize
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to run a bundled Python script (
scripts/find-god-files.py) and common CLI utilities such asrg(ripgrep) to perform static analysis on the target codebase. This behavior is aligned with the skill's primary purpose of repo reconnaissance and code consolidation.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted source code from the user's repository, which serves as a potential surface for indirect prompt injection via malicious code comments or identifiers.\n - Ingestion points: Source code files are read by the analysis script and
rgcommands in the SKILL.md instructions.\n - Boundary markers: There are no explicit instructions for the agent to treat ingested code as data only or to ignore instructions embedded within the source files.\n
- Capability inventory: The agent has broad capabilities to read, analyze, and write to the filesystem, as well as execute provided scripts.\n
- Sanitization: No content-specific sanitization or validation is applied to the source code blocks identified by the scanner before they are evaluated by the agent.
Audit Metadata