agent-macos-developer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSplaceholder to ingest user-supplied tasks into the agent's context. This creates a potential surface for indirect prompt injection where malicious instructions could be embedded in the processed input. There are no explicit boundary markers or sanitization instructions defined to mitigate this. - Ingestion points: User-supplied input via
$ARGUMENTSin SKILL.md. - Boundary markers: None identified.
- Capability inventory: The skill does not define any script-based capabilities or tool invocations.
- Sanitization: None identified.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no accompanying scripts, binaries, or executable code, which significantly limits the potential for direct system compromise.
Audit Metadata