openspec-explore

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external codebase data and project-specific markdown files, creating an attack surface where malicious content in those files could influence agent behavior.\n
  • Ingestion points: The skill reads arbitrary files from the user's codebase and specifically searches for artifacts in the openspec/changes/ directory.\n
  • Boundary markers: The instructions do not specify any delimiters or explicit warnings to isolate ingested file content from the agent's internal logic.\n
  • Capability inventory: The agent has the ability to write/modify markdown artifacts (proposals, designs, specs) and execute the openspec CLI command.\n
  • Sanitization: There are no specified procedures for sanitizing, validating, or filtering data ingested from external files.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute the openspec list --json command to gather project context. This is a local command associated with the openspec CLI, which is a declared dependency of the skill author.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 05:09 PM
Security Audit — agent-trust-hub — openspec-explore