captions
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, verbatim transcripts which serve as an ingestion point for untrusted data.
- Ingestion points: The agent reads a 'verbatim transcript' as described in the Source section of SKILL.md.
- Boundary markers: There are no instructions to use specific delimiters or to warn the agent to ignore embedded commands within the transcript text.
- Capability inventory: The skill performs file writing (creating .srt and .json files) and is instructed to perform web searches to verify names and spellings.
- Sanitization: There is no mention of sanitizing, escaping, or filtering the external transcript content for malicious instructions before the agent 'reads' and processes every line.
Audit Metadata