openspec-bulk-archive-change
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs several shell and CLI operations to manage the project state.
- Evidence: Executes
openspec list,openspec status, andopenspec sync-specsto interact with the project data (SKILL.md). - Evidence: Uses shell commands
mkdir -pandmvto restructure the file system during the archiving process (SKILL.md). - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted content from project files to drive its logic (Category 8).
- Ingestion points: The agent reads data from
openspec/changes/<name>/tasks.mdand requirement lines from markdown files inopenspec/changes/<name>/specs/(SKILL.md). - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these external files.
- Capability inventory: The agent can move files, create directories, and perform "intelligent merges" of specifications based on the data it reads (SKILL.md).
- Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the specification files before it is used to resolve conflicts.
Audit Metadata