skills/cedanl/.github/pypi-project/Gen Agent Trust Hub

pypi-project

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform standard development tasks using command-line tools such as uv, pytest, build, twine, and the GitHub CLI (gh). These are used for project synchronization, testing, building distributions, and authentication.
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and follow instructions from a repository's existing pyproject.toml file. This represents a potential indirect injection surface where untrusted data from a repository could influence agent behavior.
  • Ingestion points: Target repository's pyproject.toml file.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: File system modification, shell command execution (uv, gh, twine), and network access via publishing tools.
  • Sanitization: None specified; the agent is expected to parse the TOML file directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:15 AM