cann-ask

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses directive language to enforce its internal retrieval workflow over raw tool calls. This is a functional instruction aimed at improving response quality and does not attempt to bypass agent safety filters or extract system prompts.- [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection because it ingests and processes external documentation content.
  • Ingestion points: External wiki content is loaded into the context via the wiki_get_page tool (SKILL.md).
  • Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the fetched wiki text.
  • Capability inventory: The skill utilizes wiki_search, wiki_get_page, and wiki_submit_trajectory (SKILL.md).
  • Sanitization: No content filtering or validation procedures are defined for the retrieved data before it is presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 09:28 AM
Security Audit — agent-trust-hub — cann-ask