competitive-intel
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze data from external, untrusted sources, including competitor websites, press releases, and third-party review platforms such as G2 and Capterra.
- Ingestion points: Data collected during the 'Competitor Deep-Dive Research' and 'Competitive Signal Monitoring' steps in Phase 2, which includes website content, press releases, and user reviews (G2/Capterra).
- Boundary markers: The instructions do not define specific boundary markers or provide warnings to the agent to ignore instructions that might be embedded within the researched external content.
- Capability inventory: The skill uses a local Python script (
scripts/check-output.py) to validate the deliverable output, which involves reading and processing the generated text. - Sanitization: There are no explicit instructions for sanitizing, escaping, or filtering the external content before it is interpolated into the agent's context or the final deliverables.
Audit Metadata