create-secret
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as secret identifiers and values to manage resources via the Harness MCP server, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: User input requirements for secret creation and specification (Step 1 and Step 3 in SKILL.md).
- Boundary markers: The instructions lack specific delimiters or directions to ignore embedded instructions within user-provided values.
- Capability inventory: The skill uses harness_create, harness_update, and harness_delete tools to modify secret resources.
- Sanitization: No explicit input validation or sanitization logic is provided in the instructions.
- [SAFE]: The skill incorporates explicit safety guidelines, such as using placeholders in generated YAML instead of actual secret values. All tools, domains, and references are official Harness components, which is consistent with the skill's stated purpose and authorship.
Audit Metadata