libdoc-explain

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script rf_libdoc.py located within the plugin's internal directory to fetch keyword usage and argument details. This is standard functionality for a documentation-focused skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Robot Framework resource and library files, which could potentially contain malicious instructions intended to influence agent behavior through the documentation lookup.
  • Ingestion points: External documentation files provided via the --library, --resource, --suite, and --spec flags in SKILL.md.
  • Boundary markers: No explicit delimiters are specified to help the agent distinguish between keyword documentation and instructions.
  • Capability inventory: Subprocess execution of the local rf_libdoc.py script.
  • Sanitization: No explicit sanitization of the documentation content is mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 02:57 AM
Security Audit — agent-trust-hub — libdoc-explain