skills/desplega-ai/ai-toolbox/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides the capability to execute CLI commands directly during the verification step to automate result checking, allowing shell command execution based on definitions found in external files.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests and processes test scenarios and command strings from potentially untrusted external project plans and QA specification files.\n
  • Ingestion points: External project plans and separate Markdown QA specification documents are read to define test cases (SKILL.md, Step 1).\n
  • Boundary markers: The skill does not implement boundary markers or instructions to disregard embedded commands or malicious overrides within the ingested external content.\n
  • Capability inventory: The skill utilizes CLI command execution (SKILL.md, Step 3) and filesystem write operations for report generation and potential project configuration updates.\n
  • Sanitization: There is no evidence of validation, sanitization, or filtering applied to CLI commands extracted from external sources prior to their execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:43 PM