blog-writer
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill transforms technical documents, outlines, or raw notes into blog posts and saves them to a file. This process is vulnerable to indirect prompt injection because the agent processes untrusted data with the ability to perform file-system operations.\n
- Ingestion points: The skill ingests external data in the form of raw content, outlines, or notes from the user as described in
SKILL.md.\n - Boundary markers: The skill instructions lack explicit delimiters or instructions for the agent to ignore any malicious commands embedded within the input data.\n
- Capability inventory: The skill includes the capability to write files to the local file system at
docs/blogs/[slug].md.\n - Sanitization: No sanitization, filtering, or validation steps are performed on the ingested content before it is processed by the agent.
Audit Metadata