pdd-graph
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
pddCLI tool to retrieve and display dependency graphs. These operations are limited to informational subcommands such aspdd graph --openandpdd graph --issue. It includes explicit constraints forbidding the agent from performing mutations, such as GitHub repository modifications or triggering new workflows. - [INDIRECT_PROMPT_INJECTION]: The skill processes issue dependency data and evidence links which may originate from external sources like GitHub.
- Ingestion points: Untrusted data enters the agent context through the output of the
pdd graphcommand (SKILL.md). - Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for the data returned by the CLI.
- Capability inventory: The skill is authorized to execute the
pddcommand line utility. - Sanitization: No explicit sanitization or validation of the ingested issue data is described in the instructions, relying on the agent's internal filtering.
Audit Metadata