flaresolverr
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites retrieved via FlareSolverr. This data is then interpreted by the agent, creating a surface for indirect prompt injection where malicious instructions embedded in a webpage could manipulate the agent's behavior.
- Ingestion points: The output of the
getandpostcommands inscripts/flaresolverr, which returns the HTML body and headers of external websites into the agent's context. - Boundary markers: The skill includes a 'Mutation Gate' in
SKILL.mdrequiring user confirmation for state-changing POST requests, which provides a procedural layer of protection against unauthorized actions triggered by malicious content. - Capability inventory: The skill allows the agent to make network requests (GET/POST) to arbitrary URLs via the FlareSolverr service.
- Sanitization: The skill does not provide mechanisms to sanitize or filter the retrieved content before it is processed by the agent, relying instead on the agent's internal safety guardrails.
Audit Metadata