The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The script hunter.py executes the GitHub CLI (gh) using subprocess.run with a list of arguments. This implementation correctly avoids shell injection by not using shell=True and passing arguments as discrete list elements.\n- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill ingests untrusted repository names, descriptions, and issue titles from the GitHub API. This data could contain malicious instructions designed to manipulate an agent's behavior during Phase 3 (Feasibility Analysis) or Phase 4 (Dossier Generation).\n
Ingestion points: hunter.py (via gh api and gh issue list outputs).\n
Boundary markers: Absent. The data is printed directly to stdout without delimiters or instructions to ignore embedded commands.\n
Capability inventory: Subprocess execution of the gh utility.\n
Sanitization: None. The script does not escape or validate strings retrieved from the API before they are processed by the agent.

oss-hunter