youtube-title-creator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied video summaries to generate titles, creating a surface for potential instruction injection. Evidence Chain: 1. Ingestion points: Phase 1, Step 1 in SKILL.md where users provide content summaries. 2. Boundary markers: Absent; no delimiters or ignore-instructions are specified for the user input. 3. Capability inventory: The workflow instructs the agent to create and write output to a new markdown file. 4. Sanitization: Absent; no validation or filtering of user input is described.
- [NO_CODE]: The skill consists exclusively of markdown instructions and reference files, with no scripts or binary executables included.
- [SAFE]: No network operations, credential exposures, or privilege escalation attempts were found in the skill content or references.
Audit Metadata