sensei-assess

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard Git and GitHub CLI commands (such as git status, git diff, and gh pr view) to determine the development context. These operations are local to the environment and are required for the skill's intended dispatcher functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data that could be influenced by external contributors through repository content. * Ingestion points: The skill reads output from git diff, git log, and pull request views into the agent context. * Boundary markers: No specific delimiters are used to wrap the ingested content. * Capability inventory: The skill can execute shell commands via git and gh and route to other agent skills. * Sanitization: No sanitization or validation is performed on the data ingested from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:29 AM
Security Audit — agent-trust-hub — sensei-assess