skills/immamdouhaboammar/antigravity-superpowers/agency-threat-detection-engineer/Gen Agent Trust Hub
agency-threat-detection-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill establishes a benign persona and workflow for security operations and detection engineering. No malicious code or instructions were found.
- [PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted data such as detection rules and log files, which creates an indirect prompt injection surface.
- Ingestion points: Ingests Sigma rules (.yml) and test data (.json) from the environment for validation and compilation.
- Boundary markers: None specified in the instructions to separate data from commands.
- Capability inventory: The workflow involves shell execution of utilities like sigma-cli, python, and deployment tools (curl, az).
- Sanitization: No explicit sanitization or validation of the input content is defined in the instructions.
- [COMMAND_EXECUTION]: The provided CI/CD templates include the use of
curl -k, which disables SSL certificate verification. While common in internal enterprise environments, it is a security weakness that could lead to credential exposure via network interception.
Audit Metadata