skills/shipshitdev/skills/skill-scout/Gen Agent Trust Hub

skill-scout

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's search process involves ingesting untrusted data from external sources including web search results, GitHub repository content, and public package registries. This creates a surface for indirect prompt injection if an attacker embeds malicious instructions in public documentation or repositories that the agent might crawl.
  • Ingestion points: Processes external content from GitHub, package registries, and web searches.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for external data.
  • Capability inventory: Limited to read-only search and local file reading; delegation to other tools is required for installation or creation.
  • Sanitization: No explicit sanitization or validation of external content is defined in the search process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — skill-scout