solo-metrics-track
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from project files and incorporates it into a generated metrics plan.\n
- Ingestion points: The skill reads external project documentation, specifically the PRD and CLAUDE.md files, to extract project context and features (SKILL.md, Step 1).\n
- Boundary markers: There are no protective delimiters or specific instructions provided to the agent to disregard potential malicious instructions found within these files.\n
- Capability inventory: The agent possesses the capability to write to the local filesystem (e.g., creating docs/metrics-plan.md) via the Write tool.\n
- Sanitization: The skill lacks logic to sanitize, validate, or escape the content ingested from the project files before it is interpolated into the output template.
Audit Metadata