apple-docs
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and assets from official Apple domains, including
developer.apple.comanddocs-assets.developer.apple.com. These are well-known and trusted services. - [COMMAND_EXECUTION]: Uses standard system tools like
curlandjqvia a provided shell script (appledoc.sh) to perform documentation lookups. It also provides Python 3 snippets for text processing and HTML stripping of Apple's policy pages. All command execution is focused on the legitimate task of data retrieval and formatting. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from Apple's documentation site. This represents a potential indirect prompt injection surface; however, the risk is mitigated by the trusted nature of the source and the skill's specific field-based parsing approach.
- Ingestion points: Documentation JSON and HTML from
developer.apple.com. - Boundary markers: Instructions explicitly tell the agent to cite sources and quote only relevant sentences.
- Capability inventory: Restricted to
curlfor reading andjq/python3for processing. - Sanitization: Implements specific field extraction and HTML stripping filters.
Audit Metadata