fireflies-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests repository content which may contain untrusted data, creating a potential vector for indirect prompt injection when combined with file-writing capabilities.
- Ingestion points: Repository files accessed via Read, Glob, and Grep tools.
- Boundary markers: No explicit prompt delimiters are defined for the ingested content.
- Capability inventory: The skill has the ability to modify repository files using the Write and Edit tools.
- Sanitization: The skill contains explicit instructions to verify that no secrets or meeting-derived content entered logs or artifacts.
Audit Metadata