writing-skills
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
render-graphs.jsusesexecSyncto run the Graphvizdotutility, taking input directly from markdown blocks to generate SVG process diagrams. - [EXTERNAL_DOWNLOADS]: Documentation in
anthropic-best-practices.mdsuggests the use of external Python libraries likepdfplumberandpypdfand includes links to official Anthropic documentation images. - [PROMPT_INJECTION]: The skill methodology defines 'pressure scenarios' that use psychological persuasion principles (authority, scarcity) to test and ensure that agents do not bypass established workflows.
Audit Metadata