competitor-signals
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface via external website scraping.
- Ingestion points: Competitor case studies, testimonials, and blog posts are scraped via WebFetch in SKILL.md (Step 5).
- Boundary markers: Absent; scraped content is not isolated from instructions when processed by the agent in Step 10.
- Capability inventory: Includes Bash execution, file writing, and web searching across the skill scripts and instructions.
- Sanitization: Basic regex-based HTML stripping is performed in scripts/competitor_signals.py, but no semantic sanitization exists for the agent's analysis phase.
Audit Metadata