Skills
Navigate
skills/full-stack-skills/processon-skills/openspec-apply-change/Gen Agent Trust Hub

openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external instruction data from the openspec CLI, which could potentially influence agent behavior.\n
  • Ingestion points: The context and operationGuidance fields returned by the openspec instructions apply --json command in SKILL.md.\n
  • Boundary markers: The skill contains explicit instructions to treat this data as advisory only, prohibiting it from being used as evidence of task completion or for bypassing blocked states.\n
  • Capability inventory: The skill has capabilities to execute openspec commands via Bash and modify project source files to implement change tasks.\n
  • Sanitization: The skill relies on manual agent logic to identify and report conflicts between CLI-provided instructions and the built-in workflow.\n- [COMMAND_EXECUTION]: The skill relies on executing openspec CLI commands through Bash to manage project state, retrieve instructions, and track progress.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:50 AM