openspec-apply-change
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
openspecCLI through shell commands to list available changes, retrieve project status, and fetch implementation instructions. This is a legitimate and core functionality of the skill. - [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes dynamic JSON data from external CLI tool outputs to drive its logic.
- Ingestion points: JSON output from
openspec list,openspec status, andopenspec instructions apply(SKILL.md). - Boundary markers: Absent; there are no specific delimiters used to isolate or ignore instructions potentially embedded in the tool's output.
- Capability inventory: Shell command execution (
openspectool), file system reading (context files), and file system writing (updating task status in files) (SKILL.md). - Sanitization: Absent; the agent is directed to parse the JSON and follow the instructions provided by the tool output directly.
Audit Metadata