openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands
mkdirandmvto manage local archive directories. The paths used in these commands are dynamically populated from the output of theopenspec statuscommand. - [INDIRECT_PROMPT_INJECTION]: The skill parses the content of a local
tasks.mdfile to verify if all tasks are completed before archiving. - Ingestion points: Reads the content of
tasks.mdand the JSON output from theopenspecCLI. - Boundary markers: No explicit markers or delimiters are used to wrap the content of
tasks.mdwhen it is processed by the agent. - Capability inventory: The skill has the ability to execute shell commands (
mkdir,mv), call theopenspecCLI, and invoke sub-agents via the Task tool. - Sanitization: Variable interpolation for file paths in shell commands uses double-quotes to prevent simple path injection, but there is no validation of the content read from
tasks.md.
Audit Metadata