monitor-ai-tooling
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external AI measurement tools and project files.
- Ingestion points: Reads data from project measurement sources, tool analytics exports, and the AGENTS.md file (SKILL.md).
- Boundary markers: Lacks explicit delimiters to isolate external tool output from the agent's instructions (SKILL.md).
- Capability inventory: The agent can execute shell commands to export data and write files to the local filesystem (SKILL.md).
- Sanitization: Instructions include redacting credentials from reports but do not address the sanitization of embedded instructions in tool data (SKILL.md, references/report.md).
- [COMMAND_EXECUTION]: The skill instructs the agent to select and run read-only export commands and inspect tool documentation for tools like ast-grep and CodeGraph (SKILL.md).
Audit Metadata