reality-check
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code files from a user-specified directory for analysis. This creates an attack surface where malicious code comments or strings could attempt to influence the agent's behavior or audit results.
- Ingestion points: Reads all files in the target path using Glob, Grep, and Read tools.
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the analyzed code.
- Capability inventory: The agent has access to Bash (for git blame), Read, Grep, and Glob tools.
- Sanitization: No evidence of input sanitization or filtering of the ingested content before processing.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git blame commands on the local filesystem. While the usage is limited to identifying the age of TODO comments, providing an agent with shell access to process untrusted file paths carries inherent risks if the file paths or arguments are not strictly controlled.
Audit Metadata