qa-project-context
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project configuration files (such as package.json, pyproject.toml, and framework configs) to pre-fill the context file. While this is an ingestion surface for untrusted repo data, the instructions explicitly require the agent to present detected values to the user for confirmation before writing them.
- [COMMAND_EXECUTION]: The verification section uses standard shell commands like 'test', 'grep', and 'echo' to ensure the output file was created correctly and contains no placeholders. These commands are benign and limited to verifying the skill's own output.
- [SAFE]: The skill focuses on documentation and discovery within the local project environment. It does not perform network operations, access sensitive credentials (like .ssh or .aws folders), or attempt to persist across sessions.
Audit Metadata