Skills
skills/draculabo/antigravitymanager/openspec-sync-specs/Gen Agent Trust Hub

openspec-sync-specs

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the openspec list --json command to retrieve a list of available changes. This involves running a local CLI tool as part of its core functionality.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes natural language content from external markdown files to guide its file-system operations. Ingestion points: Reads files from openspec/changes/<name>/specs/*/spec.md and openspec/specs/<capability>/spec.md. Boundary markers: Absent; the instructions do not define strict delimiters or include warnings to ignore instructions embedded within the spec files. Capability inventory: The agent has permission to read files, write files, and execute the openspec CLI tool. Sanitization: Absent; there is no logic provided to sanitize or validate the text content within the specifications before it is used to determine edit operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 01:18 AM