transcript-polisher
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of raw transcripts from various sources, creating a standard surface for indirect prompt injection.
- Ingestion points: Processes external transcript files or text input from sources like Rev, Otter, and YouTube as described in SKILL.md.
- Boundary markers: The instructions use markdown headers and bold speaker names to structure output but do not explicitly instruct the agent to ignore instructions that might be embedded within the transcript text.
- Capability inventory: The skill definition is purely textual and does not invoke executable scripts or high-privilege system tools.
- Sanitization: No explicit sanitization or filtering of the transcript content is specified in the workflow.- [NO_CODE]: The skill consists entirely of markdown documentation, guidelines, and templates. No executable scripts (e.g., Python, JavaScript, or Shell) are included in the skill package.
Audit Metadata