prospecting

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script node scripts/run-state-check.js prospecting. This is used to verify the environment state within the repository context.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to the ingestion of potentially untrusted data. * Ingestion points: External data from 'issue filers', 'comments', 'review authors', and 'newsletter authors' as specified in SKILL.md. * Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions in the collected data. * Capability inventory: The skill calls a local node script scripts/run-state-check.js (referenced in SKILL.md). * Sanitization: No sanitization, validation, or filtering of external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 10:34 AM
Security Audit — agent-trust-hub — prospecting