unit-test-generating-unit-tests

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow where an agent processes external source code, requirements, and API specifications (Step 1 in SKILL.md). This creates a vulnerability to indirect prompt injection if the ingested data contains malicious instructions.
  • Ingestion points: Processes external code and documentation as defined in SKILL.md.
  • Boundary markers: The instructions lack specific delimiters or directions for the agent to ignore instructions embedded within the user-provided data.
  • Capability inventory: Although the skill itself is documentation-only, the agent using it may have capabilities (like file writing or execution) that could be exploited if it follows hidden instructions in the code it is analyzing.
  • Sanitization: No sanitization or validation of the input content is described or required by the skill.
  • [NO_CODE]: The skill consists entirely of Markdown files for documentation and contains no executable scripts, configuration files, or automated tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:14 AM