store-listing-assets
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it requires the agent to ingest and process untrusted user data—such as app names, descriptions, and URLs—to generate formatted store listing copy and asset specifications.
- Ingestion points: User-provided inputs gathered in the 'shared prep' step, including app names, descriptions, and privacy policy URLs as defined in SKILL.md.
- Boundary markers: The instructions do not define delimiters or provide 'ignore embedded instructions' warnings for the data being processed.
- Capability inventory: The skill suggests the use of image processing tools (e.g., ImageMagick) for asset production and involves verifying live URLs, which can be leveraged if malicious instructions are embedded in the input data.
- Sanitization: There are no specified requirements for escaping or validating the content of the user-provided fields before interpolation or tool use.
Audit Metadata