blog-repurpose
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external blog content which introduces a potential attack surface where malicious instructions could be embedded in the input data.
- Ingestion points: Step 1 ('Read & Analyze') involves reading external blog posts provided by the user or fetched from a source.
- Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' prompts to separate the blog data from the agent's core instructions.
- Capability inventory: The skill has the capability to write files to the local
repurposed/directory (Step 8). - Sanitization: There is no explicit requirement for the agent to sanitize the blog content or the resulting 'slug' used for filenames, which could potentially lead to path manipulation or data corruption if the input is crafted maliciously.
Audit Metadata