openspec-archive-change

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs file system operations by executing mkdir and mv via the shell to manage archive directories.
  • [PROMPT_INJECTION]: An indirect prompt injection surface was identified.
  • Ingestion points: Data is ingested from user input, the JSON output of openspec list --json, and the contents of tasks.md.
  • Boundary markers: Absent. The skill lacks markers to distinguish instructions from data during command interpolation of the <name> variable.
  • Capability inventory: The skill has the ability to execute shell commands and utilize the openspec CLI for system modifications.
  • Sanitization: Absent. No sanitization or validation logic is present to prevent shell metacharacters in the <name> variable from being executed in the shell context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:33 PM