update-swiftui-apis
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
fetchExternalDocumentationtool, which allows the agent to download content from arbitrary HTTPS URLs. This capability enables the agent to retrieve data from unverified third-party remote sources. - [COMMAND_EXECUTION]: The workflow requires the use of the
gh(GitHub) CLI to create pull requests (gh pr create). This requires the agent to operate in an environment with pre-authenticated access to the source repository. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external data, such as documentation transcripts and web content, without explicit boundary markers or sanitization logic.
- Ingestion points: Data is ingested from external sources using the
fetchAppleDocumentation,fetchAppleVideoTranscript, andfetchExternalDocumentationtools (SKILL.md). - Boundary markers: The skill does not implement delimiters or specific instructions to ignore embedded commands within the fetched external data.
- Capability inventory: The skill has the capability to modify the
swiftui-expert-skill/references/latest-apis.mdfile and execute GitHub CLI commands to create pull requests. - Sanitization: No evidence of input validation, escaping, or content filtering was found in the skill's instructions.
Audit Metadata