research

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists exclusively of instructional Markdown and metadata. It does not contain any executable scripts, binaries, or automated installation commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves the ingestion of content from external "primary sources" such as documentation and first-party APIs, which could theoretically contain malicious instructions designed to influence the agent.
  • Ingestion points: External primary sources including official documentation, source code, and first-party APIs as defined in the Purpose and Workflow sections of SKILL.md.
  • Boundary markers: The skill does not explicitly define the use of XML tags or other delimiters when quoting external sources in the final Markdown output.
  • Capability inventory: The agent is instructed to write findings to a Markdown file on the local filesystem and report the absolute path to the user.
  • Sanitization: No specific filtering or validation mechanisms for the external content are specified beyond the instruction to prioritize primary sources over secondary ones.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 07:32 AM