api-key-manager
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input regarding API configurations and security practices, creating a surface for indirect prompt injection.
- Ingestion points: The skill triggers on broad user queries such as "api", "api manager", and "api key manager" as defined in the metadata of
SKILL.md. - Boundary markers: Absent; the instructions do not provide delimiters or "ignore embedded instructions" warnings to the agent when processing user data.
- Capability inventory: The skill is configured with
Read,Write,Grep, andBash(npm:*)tools (referenced inSKILL.mdfrontmatter). - Sanitization: Absent; there are no instructions for the agent to sanitize, validate, or filter the external content before processing or generating configurations.
Audit Metadata