battlecard-generator
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection risk due to the ingestion and processing of untrusted external data.
- Ingestion points: The skill fetches competitor website content, social media posts, and public reviews from platforms like G2 and Capterra using tools such as
fetch_webpage,web_search, andreview-site-scraper(referenced in SKILL.md Phase 1). - Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore or isolate instructions that may be embedded in the external content fetched during the research phase.
- Capability inventory: The skill instructs the agent to write the finalized battlecard to the local filesystem (
Save to clients/...). - Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent to generate the final report.
Audit Metadata