skills/prefecthq/fastmcp/python-tests/Gen Agent Trust Hub

python-tests

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and base its actions on external repository content such as "nearby tests" and "validation requirements".
  • Ingestion points: Test modules and validation requirement files located in the repository where the skill is executed.
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions that might be embedded within the repository data being processed.
  • Capability inventory: The skill allows the agent to write new test modules and execute terminal commands to run regression tests.
  • Sanitization: There are no documented steps for validating or escaping the content retrieved from the repository files before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The documentation explicitly instructs the use of httpx2.MockTransport. httpx2 is not the standard Python library for this purpose (the standard being httpx). Referencing non-standard variations of popular libraries can lead to the installation of typosquatted or unverified packages from public registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 07:40 PM
Security Audit — agent-trust-hub — python-tests