docpact
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of the
docpactCLI tool to perform documentation-related tasks like routing (docpact route), linting (docpact lint), and diagnostic review (docpact diagnostics show). These are standard operations for the tool's intended use. - [PROMPT_INJECTION]: The skill is designed to ingest data from the repository via the
docpacttool, creating an indirect prompt injection surface where external content could potentially influence agent behavior. - Ingestion points: Data enters the agent's context through output from
docpact route,docpact lint, anddocpact diagnostics show(as seen inSKILL.mdandreferences/failure-repair-workflow.md). - Boundary markers: The skill employs structured JSON outputs and markdown templates to organize data, which helps in differentiating tool data from instructions, although it does not provide explicit guidance for the agent to ignore instructions embedded within that data.
- Capability inventory: The agent can execute shell commands via the
docpactCLI and perform file system writes to document files and metadata. - Sanitization: No specific sanitization procedures are documented for processing the content retrieved from repository files through the CLI.
Audit Metadata