write-openspec-docs
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions in
full-process.mddirect the agent to run terminal commands discovered in the documentation to verify results. While it specifies 'read-only' or 'scratch directory' operations, it essentially grants the agent permission to execute arbitrary code found within the documentation files. - [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by requiring the agent to ingest and act upon data from external sources (the documentation pages being edited) without sufficient sanitization.
- Ingestion points: Target documentation markdown files,
writing.md,full-process.md, and the project's rootREADME. - Boundary markers: None. There are no explicit instructions to ignore or delimit instructions found within the ingested files.
- Capability inventory: The agent has the capability to run shell commands in the terminal.
- Sanitization: None provided. The agent is expected to directly use the content of files to generate output and verify commands.
Audit Metadata