kijiji-ca
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external web pages on Kijiji.ca, representing a potential surface for indirect prompt injection.
- Ingestion points: Content is fetched from Kijiji.ca via
kijiji_ca__render_page,kijiji_ca__post_get_listings_similar, andkijiji_ca__read_pagetools defined inSKILL.mdandserver.json. - Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are present to separate external content from agent instructions in
SKILL.md. - Capability inventory: The skill allows network interaction with the vendor's domain (
unbrowse.ai) and the target site (kijiji.ca). - Sanitization: The skill instructions do not describe any validation or sanitization mechanisms for the data retrieved from external URLs.
Audit Metadata