skills/ahgraber/skills/sdd-explore/Gen Agent Trust Hub

sdd-explore

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends that the user install an external CLI utility called code-review-graph using the uv package manager to assist with codebase analysis.
  • [COMMAND_EXECUTION]: Directs the agent to execute the code-review-graph build command and to perform file system operations, such as creating and appending to .specs/.sdd/suggested-tools, to track tool recommendations.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to read and interpret content from the user's codebase and specifications.
  • Ingestion points: Files in the codebase and the .specs/ directory (SKILL.md).
  • Boundary markers: None identified; the skill does not use markers to separate untrusted codebase content from its instructions.
  • Capability inventory: Reading local files, writing to the .specs/ directory, and executing a specific CLI tool.
  • Sanitization: The skill does not perform sanitization of the content read from files before the agent processes it.
  • [NO_CODE]: This skill consists entirely of instructions within the SKILL.md file and does not include any accompanying scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 12:44 PM