openspec-bulk-archive-change

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the local system using the openspec CLI and standard shell utilities like mkdir and mv to manage directory structures. These operations are consistent with the skill's stated purpose of archiving project changes.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the local environment, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data is ingested from the output of openspec list --json, openspec status --json, the contents of tasks.md, and delta specification files located in openspec/changes/<name>/specs/.
  • Boundary markers: The skill does not define specific delimiters to separate these external inputs from the agent's instructions.
  • Capability inventory: The agent has the ability to execute shell commands, create and move directories, and delegate tasks to other subagents via the /openspec-sync-specs skill.
  • Sanitization: The instructions do not specify any sanitization or validation for the filenames or file contents before they are used in filesystem operations or logic decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 08:20 PM
Security Audit — agent-trust-hub — openspec-bulk-archive-change