pmstudio-arb
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from various project files including PRDs, architecture maps, and stakeholder directories. If these files contain malicious instructions, they could influence the agent during the slide generation process.
- Ingestion points: Reads from CLAUDE.local.md, PRD/, Architecture/, Operational/, and Data/ directories.
- Boundary markers: There are no explicit instructions or delimiters used to separate user-provided content from agent instructions during processing.
- Capability inventory: The skill primarily performs file reading and writing within the local workspace (e.g., Presentations/ directory).
- Sanitization: No sanitization or validation of the data read from external project files is performed before it is used to populate the presentation.
- [DYNAMIC_EXECUTION]: The skill generates a self-contained HTML slide deck that includes Mermaid.js for rendering diagrams and script-based navigation. This involves assembling executable HTML and JS content based on project templates.
- Finding: Generates HTML files with embedded JavaScript and external CDN references for Mermaid.js rendering.
Audit Metadata