transcript-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill requires manual installation of dependencies from the npm registry as described in the SKILL.md and package.json files.
- [DATA_EXFILTRATION] (LOW): The skill transmits meeting transcript data to api.cerebras.ai for processing via the OpenAI SDK. Users should ensure they trust this third-party endpoint with sensitive conversation data.
- [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). 1. Ingestion points: 'scripts/cli.ts' reads local meeting transcript files provided by the user. 2. Boundary markers: Absent; transcript content is directly interpolated into the LLM prompt in 'scripts/src/lib/extract-service.ts' without delimiters or instructions to ignore nested commands. 3. Capability inventory: 'scripts/cli.ts' performs file write operations ('fs.writeFile') to export the AI-generated analysis. 4. Sanitization: Absent; no filtering or escaping is applied to the transcript text before processing.
Audit Metadata