app-store-submission-packager
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructions direct the agent to collect and store sensitive developer information, specifically 'Developer account details (Apple ID, Team ID)' and 'Demo account credentials,' within generated markdown documentation. Storing secrets in plain-text files in the project's documentation directory increases the risk of exposure if the files are shared or committed to public version control repositories.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user-supplied data, such as app descriptions and feature lists, and interpolates them directly into generated files without sanitization.
- Ingestion points: Phase 1 (SKILL.md) user input collection for app details.
- Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present to separate untrusted data from the agent's instructions.
- Capability inventory: The agent performs file-write operations to create a documentation package in the /docs/ directory.
- Sanitization: No validation, escaping, or filtering of the user-provided content is specified.
Audit Metadata