harnass-engineer-final-audit

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute local scripts (harnass-os/scripts/agent-guard.py) and standard ecosystem tools like forge, hardhat, and anchor based on the detected project stack. While these commands are directed at local auditing tools, the ability to spawn subprocesses based on repository configuration is a sensitive capability.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it incorporates data from the repository being audited directly into its processing logic.
  • Ingestion points: The agent reads from project files including harnass-os/Audit.md, harnass-os/documents/inventory/current-state.yaml, and the repository's source code and configuration files.
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' commands to prevent the LLM from obeying instructions embedded within the files being audited.
  • Capability inventory: The skill possesses the capability to execute shell commands via Bash and write or edit files in the harnass-os/ directory.
  • Sanitization: No evidence was found of input validation or escaping of repository data before it is used to determine the agent's actions or parameters for command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 03:12 AM