marketing-app-store-optimizer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONOBFUSCATION
Full Analysis
- [OBFUSCATION]: The file
SKILL.mdcontains non-standard Unicode control characters (specificallyU+0004andU+0080) used as decorative prefixes in several section headers. While appearing to be stylistic choices, the inclusion of non-printing characters can be used to evade simple text-based security scanners. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data from the app store ecosystem, which presents an attack surface for indirect prompt injection.
- Ingestion points: The skill is instructed to research the app store landscape, analyze target audience behavior, and monitor competitor movements (
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores or isolates potential commands embedded within external content like app descriptions or user reviews.
- Capability inventory: The skill's workflow and associated wrapper script (
scripts/run.sh) facilitate the use of an agent runner that likely possesses network or file-reading tools. - Sanitization: The instructions do not define any filtering or validation processes for the data retrieved from external sources before processing.
Audit Metadata