skills/parhumm/jaan-to/detect-dev/Gen Agent Trust Hub

detect-dev

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) by design.
  • Ingestion points: The skill ingests untrusted data from the repository being audited, including manifest files (package.json, go.mod), Dockerfiles, and CI/CD pipeline configurations (Steps 2-7).
  • Boundary markers: The skill does not define specific boundary markers or instructions for the agent to ignore embedded commands within the files it reads.
  • Capability inventory: The skill possesses the capability to execute restricted git commands via Bash, Write to the outputs directory, and Edit sensitive configuration files such as jaan-to/config/settings.yaml and the project's tech.md seed file.
  • Sanitization: There is no mention of sanitization, escaping, or validation of the data extracted from the external repository files before it is processed or used to generate outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 08:42 PM