skills/boshu2/agentops/shared/Gen Agent Trust Hub

shared

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a 'Validation Contract' that establishes an indirect prompt injection surface by instructing agents to execute shell commands provided in task metadata.
  • Ingestion points: Metadata fields such as command, tests, and lint defined in validation-contract.md, which are often derived from external issue descriptions.
  • Boundary markers: Absent. The contract does not specify delimiters to separate instructions from data or warnings to ignore embedded commands.
  • Capability inventory: The documentation explicitly references executing these metadata strings using subprocess.run(command, shell=True) (logic documented in validation-contract.md).
  • Sanitization: Absent. The specification lacks requirements for escaping or validating input before shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 11:08 PM