goose-blog-post
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content in the form of drafts, notes, or outlines to generate blog posts.
- Ingestion points:
SKILL.md(Step 2: Retrieval of user drafts or notes). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' directives when processing the user's input.
- Capability inventory: The skill can create directories, write files (
index.md,authors.yml), and interact with the GitHub CLI (gh). - Sanitization: No explicit sanitization or validation of the user-provided text is defined.
- This is a standard risk surface for skills that process and reformat external data, as malicious content within a draft could theoretically attempt to influence the agent's task execution.
Audit Metadata