sdlc-ask-wiki

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git, grep, and a local Python tool (.wiki-llm/tools/wiki_llm.py) to search and read documentation files. These commands are executed within the project directory to retrieve information for the user.
  • [PROMPT_INJECTION]: The skill contains strong safety directives in SKILL.md explicitly instructing the agent to never create, edit, delete, or commit files. It enforces a read-only boundary by routing write requests to other specific skills.
  • [DATA_EXFILTRATION]: While the skill reads project documentation, it does not contain patterns for transmitting this data to external or untrusted domains. Its operations are restricted to the local workspace and the project's configured Git remote.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 11:06 AM