doc-tspec-validator

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts (e.g., 'validate_utest.py', 'validate_all_tspec.sh') to perform document validation, quality scoring, and cross-document checks within the 'ai_dev_ssd_flow/' directory.
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by processing untrusted Markdown documentation from the 'docs/10_TSPEC/' directory. This is highlighted by the inclusion of an '--auto-fix' flag which grants the skill file-modification capabilities based on the analysis of these documents.
  • Ingestion points: Markdown files located in 'docs/10_TSPEC/'.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined.
  • Capability inventory: Execution of local validation scripts and modification of local files via auto-fix functionality.
  • Sanitization: No sanitization of input document content is specified in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 08:50 AM