loops
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from documentation pages at https://loops.so/docs/. This untrusted content could potentially contain instructions aimed at manipulating the agent's behavior.
- Ingestion points: Documentation URLs specified in SKILL.md, including the index at https://loops.so/docs/llms.txt.
- Boundary markers: Absent. The instructions do not include delimiters or specific guidance to ignore instructions found within the documentation.
- Capability inventory: The skill spawns sub-agents via the Task tool to perform research, which may involve executing further tools based on findings.
- Sanitization: Absent. There is no evidence of filtering or sanitizing the retrieved documentation content.
Audit Metadata