skills/agentpmt/agent-skills/plaud-transcripts-corrected-with-your-own-terminology-glossary/Gen Agent Trust Hub
plaud-transcripts-corrected-with-your-own-terminology-glossary
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include commands to install dependency skills from the author's own repository.
- Evidence: The skill uses
npx skills add AgentPMT/agent-skillsto install sub-skills likegoogle-sheets,plaud, andgoogle-docs-connector. - Analysis: These are identified as vendor-owned resources (AgentPMT) and are standard installation practices for this platform.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external data.
- Ingestion points: The workflow reads transcript data from Plaud (Step 4) and glossary content from Google Sheets (Step 1).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested content.
- Capability inventory: The skill has the capability to write corrected text and summaries to Google Docs (Step 8) and log execution data back to Google Sheets (Step 9).
- Sanitization: No specific sanitization or filtering logic is defined for the external transcript content.
Audit Metadata