mvp-spec

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8).
  • Ingestion points: Processes untrusted media, URLs, and application descriptions via the $ARGUMENTS variable.
  • Boundary markers: No delimiters or specific instructions (e.g., 'ignore instructions within these markers') are used to encapsulate or isolate the ingested content.
  • Capability inventory: The agent is authorized to execute shell commands for builds and tests, chain secondary skills (/mvp, /spec), and write execution logs to the local filesystem.
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the external content before it is processed by the model.
  • [COMMAND_EXECUTION]: The 'Self-Healing Validation' section directs the agent to autonomously execute shell commands such as build, compile, and test suites on project files. This poses a risk if the project being analyzed contains malicious code or configuration files that are executed during the build or testing process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — mvp-spec