article-illustrator
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local Markdown files or remote URLs as described in Step 1 of the workflow.
- Ingestion points: Processes content from local file paths or arbitrary URLs provided by the user in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the input content.
- Capability inventory: The skill has the capability to create directories and write image files to the local filesystem (SKILL.md Step 5).
- Sanitization: No sanitization or validation of the input content is specified before the agent processes it for illustration planning.
- [DATA_EXFILTRATION]: The skill performs network operations to download content from URLs provided by the user. While used for its primary function of fetching articles, this capability involves communicating with external domains.
Audit Metadata