signals-synthesis

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted data from multiple external sources, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: The skill reads signal data (Slack, HubSpot, transcripts, etc.) from the pm-workspace-docs/signals/ directory and a hypothesis index from pm-workspace-docs/hypotheses/_index.json.
  • Boundary markers: No delimiters or instructions are provided to the agent to distinguish between its own operational guidelines and instructions that may be embedded within the source signals.
  • Capability inventory: The skill outputs actionable agent commands such as /hypothesis new, /hypothesis validate, and /hypothesis commit. Malicious content within the ingested signals could potentially influence or control these output commands.
  • Sanitization: The workflow does not specify any sanitization, filtering, or validation steps for the content of the ingested signals before they are processed for synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:31 PM