Skills
Navigate
skills/soia-team/soia-open-skills/soia-pkm-clip-github-repo/Gen Agent Trust Hub

soia-pkm-clip-github-repo

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/gen_repo_catalog.py script executes git commands (clone, remote, log) using subprocess.run(). The commands are passed as lists, which is a secure practice that prevents shell injection.
  • [EXTERNAL_DOWNLOADS]: The skill downloads repository data from GitHub using git clone. This is the intended behavior of the skill and targets a well-known technology service.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it extracts and processes text from external README.md files.
  • Ingestion points: scripts/gen_repo_catalog.py reads README content from cloned repositories.
  • Boundary markers: The extracted summaries are placed in Markdown files without explicit delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The skill has permissions to write to the local file system (Obsidian vault) and execute git commands.
  • Sanitization: The clean_line function filters HTML tags and Markdown syntax, and is_command_like attempts to identify and skip lines that look like shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:21 AM
Security Audit — agent-trust-hub — soia-pkm-clip-github-repo