openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands (
mkdir,mv) and uses theopenspecCLI to manage files and directories within local project paths. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of external data.
- Ingestion points: Reads
tasks.mdand parses JSON output fromopenspec listandopenspec statuscommands. - Boundary markers: Absent; no delimiters or ignore-instructions are used when processing external content.
- Capability inventory: Filesystem operations (
mkdir,mv) and subagent invocation for additional tasks. - Sanitization: Absent; the skill does not explicitly validate or filter content from files or tool outputs before it is used to influence agent logic.
Audit Metadata