goals
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a project management utility with no indicators of malicious activity. It primarily interacts with the local file system and a system CLI to perform its functions.
- [COMMAND_EXECUTION]: Technical analysis shows the skill executes the 'ao goals' CLI tool for project measurement (e.g., 'ao goals measure --json') and uses 'scripts/validate.sh' for internal structure verification.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted local data. 1. Ingestion points: Reads local files including README.md, PRODUCT.md, and retrospective logs in .agents/retros/. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local CLI commands and shell scripts. 4. Sanitization: No explicit content sanitization or instruction filtering is performed on the ingested data.
Audit Metadata