search-first

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it directs the agent to search for and evaluate content from external, untrusted sources such as npm, PyPI, and GitHub.
  • Ingestion points: The workflow (SKILL.md) ingest package descriptions, README files, and documentation from external repositories into the agent's context during the 'Parallel Search' and 'Evaluate' phases.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes retrieved external content.
  • Capability inventory: The agent is instructed to perform package installations (npm, PyPI) and code generation based on the research findings (SKILL.md).
  • Sanitization: There are no requirements for the agent to sanitize or validate the content retrieved from external sources before it influences the agent's implementation decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:43 AM
Security Audit — agent-trust-hub — search-first