docs-comparison-pages
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch data from external, untrusted competitor websites to verify facts and pricing, which creates an attack surface for indirect prompt injection.
- Ingestion points: The procedure in
SKILL.md(Step 2) requires the agent to fetch external pricing pages, feature/limits pages, and documentation using tools like Firecrawl or WebFetch. - Boundary markers: There are no instructions for the agent to use delimiters or specific safety markers to ignore instructions potentially embedded in the fetched external content.
- Capability inventory: The skill involves reading data from external network sources and writing generated content; it also mentions the use of
test-playwrightto verify migration snippets. - Sanitization: The instructions lack requirements for sanitizing, validating, or filtering the content retrieved from external URLs before it is processed by the agent.
Audit Metadata