pocket-recordings-transcripts
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, unauthorized data access, or obfuscation were detected. The skill interacts exclusively with AgentPMT's infrastructure and trusted vendor domains.\n- [EXTERNAL_DOWNLOADS]: Skill instructions reference installation of additional tools from the AgentPMT/agent-skills repository, which is a recognized vendor resource.\n- [PROMPT_INJECTION]: Evaluated the risk of indirect prompt injection from processed transcripts. (1) Ingestion points: Recording transcripts and AI-generated summaries retrieved via the get_recording tool. (2) Boundary markers: None present to delimit external content. (3) Capability inventory: Remote API communication and file storage operations. (4) Sanitization: Not documented.
Audit Metadata