Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an input for Instagram captions which creates a surface for indirect prompt injection. 1. Ingestion points: SKILL.md (post_caption input). 2. Boundary markers: None; untrusted text is processed directly. 3. Capability inventory: Subprocess calls to the refly CLI (SKILL.md). 4. Sanitization: No sanitization or input validation logic is specified in the skill definition.
Audit Metadata