swift-valkey
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates reading data from external Valkey/Redis databases, which establishes a potential surface for indirect prompt injection if the database content is untrusted. (1) Ingestion points: Data retrieval operations such as get and hgetall in SKILL.md. (2) Boundary markers: No specific delimiters or instructions to ignore embedded prompts are provided in the examples. (3) Capability inventory: The skill allows the agent to perform read and write operations on database servers. (4) Sanitization: The provided code patterns do not include sanitization or validation of the retrieved database content.
- [EXTERNAL_DOWNLOADS]: The skill documentation references the official valkey-swift repository on GitHub for dependency management via Swift Package Manager.
- [SAFE]: The technical patterns in references/valkey-patterns.md demonstrate a security-conscious approach by implementing depth-limited parsing to protect the application from potential stack overflow attacks during the processing of nested protocol tokens.
Audit Metadata