meeting-intelligence-system-skill

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted meeting transcripts, notes, and recordings which could contain malicious instructions designed to override the agent's behavior during analysis.
  • Ingestion points: Untrusted meeting transcripts, notes, and recordings provided by the user (as described in SKILL.md).
  • Boundary markers: The instructions do not specify the use of boundary markers or delimiters to isolate the transcript content from the analysis instructions.
  • Capability inventory: The skill has the capability to write files to the local filesystem (telemetry log).
  • Sanitization: There are no instructions to sanitize or validate the content of the transcripts before processing them.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform a file-write operation to a specific local path to log session metadata.
  • Evidence: The 'Emit Outcome Sidecar' section in SKILL.md directs the agent to write a JSON block to ~/.claude/skill-analytics/last-outcome-meeting-intelligence-system.json.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:56 AM
Security Audit — agent-trust-hub — meeting-intelligence-system-skill