skills/florianbruniaux/claude-code-ultimate-guide/source-command-ccguide-init-docs/Gen Agent Trust Hub
source-command-ccguide-init-docs
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches approximately 1.2MB of official documentation from Anthropic to establish a local baseline snapshot.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data which could potentially contain instructions targeting the AI agent.
- Ingestion points: The skill uses a tool to download documentation from a remote source as described in
SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are identified to wrap the ingested content.
- Capability inventory: The skill performs file system writes to the
~/.cache/Codex-guide/directory. - Sanitization: No evidence of validation or sanitization of the remote content is provided before storage.
Audit Metadata