folk-recon
Warn
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to run complex search commands (find,grep,xargs) across the workspace to identify specific HR-related files. - [DATA_EXFILTRATION]: The skill's primary function is to discover and process highly sensitive information such as salary bands, equity structures, compensation details, and organizational charts. This creates a significant surface for sensitive data exposure within the agent's context.
- [PROMPT_INJECTION]: The skill reads data from local CSV, JSON, and Markdown files (Ingestion points: Step 0 file scanning). It does not employ boundary markers or instructions to ignore embedded commands (Boundary markers: Absent). The agent has access to
Bash,WebFetch, andRead(Capability inventory: SKILL.md). There is no validation or filtering of the file contents before processing (Sanitization: Absent). This creates a surface for indirect prompt injection.
Audit Metadata