openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing multiple subprocess commands via the openspec CLI (e.g., openspec status, openspec list, and openspec instructions) to retrieve state and metadata for the implementation process.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes content from external project artifacts that could be controlled by an attacker.
  • Ingestion points: The agent reads files identified in the contextFiles list provided by the CLI (e.g., proposal, specs, design, tasks) and parses JSON output from CLI commands.
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded natural language instructions within the processed files.
  • Capability inventory: The skill has permission to execute shell commands (openspec) and perform file system modifications (writing code changes and updating task checkboxes).
  • Sanitization: None. The skill lacks validation or sanitization of the content found within the context files before using it to guide implementation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 06:40 PM
Security Audit — agent-trust-hub — openspec-apply-change