validation-plan-artifacts

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from project artifacts, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads and understands external files such as requirements.md, data-model.md, and contracts/api.yaml (SKILL.md, Step 1).
  • Boundary markers: There are no explicit delimiters or instructions defined to isolate the content of the artifacts being reviewed from the agent's instruction set.
  • Capability inventory: The skill has the capability to run a local Python script (scripts/check-artifacts.py) to perform automated validation on files.
  • Sanitization: No sanitization or validation of the input data is performed before it is processed by the agent or passed to the validation script.
  • [COMMAND_EXECUTION]: The skill executes a local Python script as part of its automated validation workflow.
  • Execution method: The skill instructions in references/PHASE-CHECKLISTS.md specify running 'python scripts/check-artifacts.py' on local files.
  • Functional purpose: The script identifies unresolved markers, validates traceability, and checks for PII sensitivity annotations.
  • Security context: This is a legitimate functional capability provided by the skill author for document linting and does not require elevated privileges or external connectivity.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:41 PM