assertion-quality

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to ingest and process user-provided test and production code to evaluate assertion depth. This ingestion of untrusted external data presents a potential surface where malicious instructions embedded in the source code could attempt to influence the agent's analysis or reporting behavior.
  • Ingestion points: The workflow identifies test and production code provided by the user (described in the Inputs section) and gathered during Step 2 as the primary data sources.
  • Boundary markers: The instructions do not specify the use of clear delimiters or instructions for the agent to ignore embedded commands within the analyzed code blocks.
  • Capability inventory: The skill's scope is limited to reading files and generating text-based metrics and recommendations. It does not include capabilities for subprocess execution, network communication, or writing to the file system, which mitigates the impact of potential injections.
  • Sanitization: There are no explicit requirements for sanitizing, escaping, or validating the content of the ingested code before it is processed for assertion classification.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 12:34 AM
Security Audit — agent-trust-hub — assertion-quality