codebase-onboarding
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it systematically processes untrusted data from the user's codebase.
- Ingestion points: The workflow in Phases 1 through 5 requires the agent to scan the entire repository, including source files,
.envconfigurations, and package manifests (SKILL.md). - Boundary markers: No specific delimiters or instructions are provided to the agent to disregard instructions found within the code or comments it analyzes.
- Capability inventory: The agent has the ability to read arbitrary files, create directories, and write documentation files to the
docs/directory. - Sanitization: There is no evidence of filtering or sanitization of the content extracted from the codebase before it is used to generate documentation or influence the agent's summary.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to gather project metadata.
- Evidence: The instructions specifically mention using
git rev-parse --short HEADto populate documentation headers (SKILL.md). This is a benign use of development tools for technical documentation.
Audit Metadata