skill-creator
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and generate instructional content for AI agents, which is an inherent attack surface for indirect prompt injection. A malicious user could provide input designed to override agent behavior during the skill creation process.
- Ingestion points: User-provided inputs during the skill creation workflow (SKILL.md).
- Boundary markers: None explicitly defined in the templates to separate user instructions from system guidelines.
- Capability inventory: The skill itself contains no subprocess calls, network operations, or file-writing scripts; it provides a markdown framework for the agent to follow manually or via platform tools.
- Sanitization: None observed; the skill relies on the agent's native handling of markdown content.
- [NO_CODE]: The skill consists entirely of Markdown documentation and templates. No scripts, binaries, or automated configuration files are present in the provided files.
Audit Metadata