openspec-apply-change
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes dynamic data from the openspec CLI, including context and guidance that influence agent behavior.
- Ingestion points: Output from the
openspec instructions applycommand in SKILL.md. - Boundary markers: The skill does not define explicit delimiters for parsing tool output.
- Capability inventory: Uses the Bash tool to execute CLI commands and modifies local project files.
- Sanitization: Instructs the agent to treat external guidance as advisory and prioritize the core workflow.
- [COMMAND_EXECUTION]: The skill executes various subcommands of the openspec CLI tool using the Bash tool to manage changes and implementation tasks, which is the primary intended function of the skill.
Audit Metadata