oc-ted-talk
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill instructions and metadata found no evidence of malicious intent, obfuscation, or unauthorized data access. The skill serves its stated purpose as a creative writing assistant.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided technical insights at runtime.\n
- Ingestion points: Technical insights provided by the user (SKILL.md).\n
- Boundary markers: None specified in the instructions to delimit user input from instructions.\n
- Capability inventory: None. The skill does not include scripts, subprocess calls, or network operations.\n
- Sanitization: None present.\n
- Note: Due to the lack of executable capabilities in the skill itself, the impact of potential injection is limited to the quality of the generated text output.
Audit Metadata