subagent-explore-report

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external repository files, which represents a potential attack surface if those files contain malicious instructions.
  • Ingestion points: The agent reads local project files including README, CMakeLists.txt, and source code files (main.c, app.c) as specified in the Steps section of SKILL.md.
  • Boundary markers: Absent. The instructions do not include specific delimiters or warnings to ignore instructions found within the analyzed files.
  • Capability inventory: The skill is explicitly restricted to read-only operations (glob, grep, read). It does not invoke file-writing, network-sending, or code-execution tools.
  • Sanitization: Absent. Content is processed and summarized directly into a report format.
  • [EXTERNAL_DOWNLOADS]: The documentation includes a reference link to a GitHub repository (https://github.com/thecuriousts/premflow) for provenance. This is a static reference link to a well-known service and does not involve automated script execution or package installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:46 AM
Security Audit — agent-trust-hub — subagent-explore-report