hig

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a collection of static markdown documentation files extracted from official sources and does not contain any executable scripts, binaries, or high-risk command execution patterns.
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides the agent with instructions to fetch additional guidelines from a third-party mirror at sosumi.ai if the required information is not found in the local files. This is a functional requirement for providing a comprehensive documentation lookup service.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process a large volume of documentation, which presents a surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read local markdown files and fetch remote documentation from sosumi.ai.
  • Boundary markers: Absent; the skill does not provide explicit markers or instructions to differentiate between documentation content and system instructions.
  • Capability inventory: The agent is encouraged to use grep and standard file reading tools to parse the documentation corpus.
  • Sanitization: Absent; content from the documentation files is processed as raw text without validation or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 08:18 PM
Security Audit — agent-trust-hub — hig