hunt-forgot-password
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and analyze data from external targets (web application responses).
- Ingestion points: The agent is directed to record the response body and compare responses from external forgot-password endpoints in SKILL.md.
- Boundary markers: No specific boundary markers or ignore instructions warnings are specified for the ingested target data to prevent potential command interpretation from external sources.
- Capability inventory: The skill utilizes network request capabilities (POST to endpoints) to interact with external services.
- Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is processed by the agent.
Audit Metadata