action-continuity-choreography-by-1picsey
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze content from external URLs (goodcase.ai and x.com) to use as reference material for prompt generation. This creates an attack surface for indirect prompt injection if the target websites were to contain malicious instructions designed for the AI.
- Ingestion points: External media and case study URLs provided in
references/cases.md. - Boundary markers: The skill instructs the agent to "Distinguish observed evidence from your own recommendation" and verify if media was accessible before claiming visual fidelity.
- Capability inventory: Requires the use of browser, image, or video inspection tools to analyze remote assets.
- Sanitization: No specific technical sanitization or filtering is mentioned for the external content.
- [SAFE]: The skill includes clear safety constraints that prevent the agent from making external account changes or uploading private assets without explicit user approval. It also mandates proper attribution to the original creators of the referenced cases.
Audit Metadata