code-standards

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow requires the agent to execute shell-based commands for repository analysis. Evidence: The skill defines the use of git rev-list, git diff, and grep to check for codebase staleness and extract coding conventions (SKILL.md, Workflow Steps 2 and 3).
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its reliance on scanning untrusted codebase data to influence documentation and subsequent agent behavior. * Ingestion points: The skill reads metadata from the existing docs/code-standards.md file and performs broad codebase scans for conventions (SKILL.md, Workflow Step 2 & 3). * Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from obeying instructions embedded within the code snippets it scans. * Capability inventory: The skill utilizes codebase-wide search tools (grep), repository history tools (git), and filesystem write operations (SKILL.md, Workflow Step 3 & 4). * Sanitization: No sanitization or validation logic is provided to filter out potentially malicious content found during the codebase scan before inclusion in the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:28 PM
Security Audit — agent-trust-hub — code-standards