doc-ctr

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected. The skill processes content from multiple upstream documents to generate contract artifacts.
  • Ingestion points: Requirement and design documents located in docs/01_BRD/ through docs/07_REQ/.
  • Boundary markers: Absent; there are no delimiters specified to isolate external document data from agent instructions.
  • Capability inventory: The skill can execute local shell and Python scripts for validation and manage the filesystem via mkdir.
  • Sanitization: Absent; the skill does not specify any sanitization or validation of the text content ingested from upstream layers.
  • [COMMAND_EXECUTION]: The skill directs the agent to execute several shell commands and local scripts for workflow management.
  • Evidence: Usage of ls for file verification and mkdir -p for structure setup.
  • Tool Execution: Runs validation tools like yamllint and openapi-spec-validator.
  • Local Framework Scripts: Executes validation scripts including validate_ctr.sh, validate_tags_against_docs.py, and validate_cross_document.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 04:25 AM