ios-app-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing local project files, source code, and build configurations, which represents an attack surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The 'Project Preflight' section in
SKILL.mdinstructs the agent to inspect workspace files, project settings, existing source code, and Git status. - Boundary markers: The 'Completion' section in
SKILL.mdincludes a boundary instruction stating: 'Do not commit, push, publish, change signing, or mutate external systems unless the user authorized that action.' - Capability inventory: The skill has capabilities to modify the local file system (Implementation step) and execute build/test commands via the environment (Verification step).
- Sanitization: There are no explicit instructions for sanitizing or escaping the content of the files ingested during the preflight phase.
Audit Metadata