pmstudio-dr
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on analyzing internal product documentation to generate its output, creating a potential vector for indirect prompt injection if these files contain malicious instructions.\n
- Ingestion points: The skill instructions direct the agent to read
CLAUDE.local.md, architecture diagrams inArchitecture/, integration requirements inPRD/, and existing incident response plans inOperational/IRP-*.html.\n - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the content of these files as data only or to ignore embedded natural language instructions.\n
- Capability inventory: The skill allows the agent to read multiple files across the project directory and write the resulting disaster recovery plan as a self-contained HTML file to
Operational/DR-Plan-*.html.\n - Sanitization: No sanitization or validation logic is specified to filter or escape content retrieved from the source documents before it is processed or written to the output file.
Audit Metadata