update-docs
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes bash commands including git, find, and grep to perform repository analysis and project discovery. These tools are used appropriately for the skill's stated purpose of updating documentation based on code changes.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8).
- Ingestion points: The skill reads source code diffs and existing documentation files through git and find commands.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions embedded within the processed files.
- Capability inventory: The agent has permission to use bash for command execution and tools for writing or editing files.
- Sanitization: No sanitization or content validation is performed on the ingested data before analysis.
Audit Metadata