ss-show-spec
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by instructing the agent to read and display the full text of documentation files found in the openspec/ directory. This content is then processed as part of the agent's context.
- Ingestion points: Content is read from openspec/specs/spec.md and openspec/changes/archive/ spec files.
- Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent to treat file content as untrusted data or to ignore instructions embedded within it.
- Capability inventory: The skill utilizes the agent's file system read capabilities. No other high-risk capabilities like network access or command execution are invoked.
- Sanitization: Absent. There is no evidence of content validation, escaping, or filtering before the data is displayed to the user or processed by the agent.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not include any accompanying Python or Node.js scripts, binaries, or other executable components.
Audit Metadata