to-story
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of instructional Markdown content and configuration metadata. There are no executable scripts, binaries, or runtime dependencies included within the file set.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-supplied ticket drafts, which represents a potential surface for indirect prompt injection. However, given the skill's lack of system capabilities (no network, shell, or filesystem permissions), this surface does not pose a functional security risk.
- Ingestion points: User-provided draft tickets, Jira issues, or GitHub issues (SKILL.md).
- Boundary markers: None explicitly defined for the ingested text.
- Capability inventory: None. The skill's permissions.yaml explicitly disables all tool and system capabilities.
- Sanitization: None performed on the input text before processing.
- [SAFE]: The skill follows security best practices by including a restrictive capability manifest (permissions.yaml) that explicitly limits the environment to 'knowledge' only, disabling shell execution, network access, and filesystem writes.
Audit Metadata