retention-editor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, specifically video transcripts and timeline metadata, to calculate edit points.
- Ingestion points: Ingests transcript text and timeline metadata as described in the 'DERIVE FIRST' and 'CRAFT' sections of SKILL.md.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions that might be embedded within the transcripts.
- Capability inventory: The skill utilizes the 'cutRanges' capability to modify user files (video timelines) and references the 'agentWorkspace action specialist_consult' tool.
- Sanitization: Absent. There is no explicit requirement to sanitize or validate the content of the transcript before it is used to determine edit ranges.
Audit Metadata