debug-my-harness
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and interprets data from an external file (
.vigiles/runs.jsonl) to diagnose system behavior. - Ingestion points: Reads records from the
.vigiles/runs.jsonllog file. - Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore potentially malicious instructions embedded within the JSONL records.
- Capability inventory: The skill is limited to reading the file and providing analysis; it does not perform writes, network requests, or command execution.
- Sanitization: There is no evidence of sanitization or validation of the JSON records before they are processed by the agent.
Audit Metadata