blast-radius

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of code changes, diffs, and schemas (SKILL.md).
  • Ingestion points: Reads source code diffs, changed symbols, call sites, producers, consumers, and schemas from the working directory.
  • Boundary markers: The instructions do not define specific delimiters or instructions to the agent to disregard embedded directives within the analyzed code.
  • Capability inventory: The agent has the capability to read files, perform symbol searches, and execute dynamically generated scripts or tests.
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from the analyzed files before it is processed by the agent.
  • [DYNAMIC_EXECUTION]: The skill instructions direct the agent to "Add a disposable script or focused public-contract test" to prove safety invariants (SKILL.md).
  • This involves generating and executing code at runtime based on the analysis of the project's codebase.
  • While this is a primary function of the tool for verification, it presents a potential execution vector if the codebase being analyzed contains malicious content intended to exploit the test-generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:00 AM
Security Audit — agent-trust-hub — blast-radius