skills/neonwatty/linkparty/gen-test/Gen Agent Trust Hub

gen-test

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run npx vitest run to verify the generated test files. This execution is necessary for the skill's primary purpose of test verification.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external source files to generate test cases, creating a potential surface for indirect instructions.
  • Ingestion points: Reads source code from the path provided in $ARGUMENTS (SKILL.md).
  • Boundary markers: None defined to isolate source code from the agent's instructions.
  • Capability inventory: Includes the ability to execute shell commands via npx vitest (SKILL.md).
  • Sanitization: No sanitization or validation of the input file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 08:45 PM