create-tests

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface where the agent processes content from a user-provided file to generate and run code.
  • Ingestion points: The skill ingests untrusted data from issue-analysis-<issue_number>.md (Step 1).
  • Boundary markers: Absent. There are no delimiters or explicit instructions provided to the agent to differentiate between the analysis content and its own instructions.
  • Capability inventory: The skill instructs the agent to 'Run & Verify the Tests' (Step 4), which involves executing code generated from the external data.
  • Sanitization: Absent. No validation or sanitization of the input file's content is described.
  • [NO_CODE]: This skill is composed entirely of natural language instructions in a Markdown file and does not include any executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 08:10 AM