geo-citability

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to retrieve and analyze untrusted data from external sources, which could contain instructions intended to manipulate the agent's behavior.
  • Ingestion points: The WebFetch tool is used in SKILL.md (Step 1) to retrieve content from external URLs provided at runtime.
  • Boundary markers: The analysis procedure does not specify the use of delimiters or 'ignore' instructions to separate the fetched content from the agent's internal instructions.
  • Capability inventory: The skill frontmatter allows the use of high-privilege tools such as Bash, Write, and WebFetch across all operations.
  • Sanitization: No explicit content sanitization, validation, or filtering of the retrieved web data is defined before the information is processed for scoring and reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:53 PM
Security Audit — agent-trust-hub — geo-citability