openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
openspecCLI to list and verify the status of changes. It also uses standard shell commandsmkdirandmvto manage the archive directory structure within the project folder. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and processes untrusted data from the file system and CLI outputs.
- Ingestion points: The skill reads the contents of
tasks.mdand parses the JSON output fromopenspec listandopenspec statuscommands inSKILL.md(Steps 1, 2, and 3). - Boundary markers: There are no explicit delimiters or instructions defining the boundaries of the external content being processed.
- Capability inventory: The skill possesses file system modification capabilities (
mkdir,mv) and execution of theopenspecCLI based on state assessments. - Sanitization: No specific sanitization or validation of the content within
tasks.mdis performed beyond searching for markdown checkbox patterns.
Audit Metadata