knoxhub-blog

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The SKILL.md file (Step 1) specifies fetching content from user-provided URLs via WebFetch and gathering data via WebSearch.
  • Boundary markers: Instructions do not include the use of delimiters or warnings to ignore instructions embedded in the external content.
  • Capability inventory: The skill is configured with access to Bash, Read, Write, Glob, and Grep in the SKILL.md frontmatter, which could be exploited if an injection occurs.
  • Sanitization: There is no mention of validating or cleaning the content retrieved from external sources before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 08:18 AM