competitive-pricing-intel
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external competitor websites, which are untrusted sources.
- Ingestion points: The skill utilizes the
fetch_webpagetool to scrape live competitor pricing pages and historical snapshots fromweb.archive.org. It also usesweb_searchto gather public announcements and community discussions. - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore potentially malicious instructions embedded within the scraped HTML or community forum text (e.g., instructions intended to hijack the agent's persona or exfiltrate data).
- Capability inventory: The skill possesses the ability to read from the web (
fetch_webpage,web_search) and write analysis reports to the local filesystem (Save to clients/...). - Sanitization: There are no instructions for sanitizing or filtering external content before it is processed for analysis.
Audit Metadata