oc-hook-finder
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of transcript data and steering directives. Malicious content within these inputs could potentially override the agent's logic for selecting or ranking content.\n
- Ingestion points: The skill reads transcript and analysis data from the local file system (transcript.json, analysis.json) and honors a STEERING variable provided at runtime as described in SKILL.md.\n
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat ingested data as non-executable text.\n
- Capability inventory: The skill is configured to use Bash and Read tools which are available to the agent during execution.\n
- Sanitization: The instructions do not include any logic for validating, filtering, or escaping the external content before it is processed by the agent.
Audit Metadata