skills/hashintel/labs/contract/Gen Agent Trust Hub

contract

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted external data.
  • Ingestion points: The skill reads concept capsules, recent activity cards, and existing source code files from the local project (SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the ingested source files.
  • Capability inventory: The skill possesses the ability to write to the filesystem (docs/contracts.md) and execute shell commands for code verification and git commits (SKILL.md).
  • Sanitization: The instructions lack explicit requirements for sanitizing or escaping the content read from external source files before processing.
  • [COMMAND_EXECUTION]: The skill performs shell-based operations including running a "verification harness" and executing git commits (SKILL.md). While these are typical actions for a development assistant, they represent the execution of local system commands based on the state of the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:31 AM
Security Audit — agent-trust-hub — contract