openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves context and operational guidance from external CLI commands which could potentially contain malicious instructions.
- Ingestion points: SKILL.md (Step 1 and Step 4) specifies running
openspec instructionsto fetch JSON metadata. - Boundary markers: The skill contains detailed instructions to treat fetched context as "advisory" and to prioritize "built-in steps, explicit user choices, resolved paths, CLI checks, and command contracts" over external guidance.
- Capability inventory: The skill utilizes directory creation (
mkdir), file movement (mv), and CLI execution (openspec). - Sanitization: The instructions explicitly mandate reporting conflicts and forbid the verbatim copying of external text into specification files or archive summaries.
- [COMMAND_EXECUTION]: The skill uses shell commands to manage the repository structure and query project state.
- Executes
openspecCLI tools to list changes, check status, and perform archive operations. - Uses standard filesystem commands
mkdirandmvto organize thearchive/directory, which is consistent with the skill's stated purpose.
Audit Metadata