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 scriptscripts/run-state-check.js(referenced inSKILL.md). * Sanitization: No sanitization, validation, or filtering of external content is described.
Audit Metadata