Geek-skills-openspec-explore
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
openspec list --jsonto retrieve the status of active changes and project metadata. This is a standard operation for the tool's stated purpose. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external content from the codebase and project-specific artifacts (such as
proposal.md,design.md, andtasks.md). - Ingestion points: Reads files within the
openspec/changes/directory and general codebase files. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed files are defined.
- Capability inventory: The skill can read files and execute specific
openspecCLI commands. - Sanitization: No sanitization or validation of the content within the ingested files is performed before processing.
Audit Metadata