openspec-continue-change

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various commands using the openspec CLI tool, including openspec list, openspec status, and openspec instructions, to retrieve project metadata and workflow state.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external data to guide agent behavior.
  • Ingestion points: The agent parses JSON data from the openspec CLI, specifically the context, rules, template, and instruction fields.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the CLI-provided content as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill has the capability to execute local CLI commands and perform file read/write operations on the local file system.
  • Sanitization: There is no evidence of sanitization or validation performed on the strings retrieved from the CLI before they are used to influence file creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 04:53 AM