spec-writer
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data like project briefs and material lists to generate documents.
- Ingestion points: Data is retrieved from materials briefs and source catalogs via the Read tool (SKILL.md).
- Boundary markers: The skill lacks explicit instructions for using delimiters or warnings to ignore embedded instructions in the processed data.
- Capability inventory: The skill has access to Write, Edit, and Bash tools to manipulate the environment (SKILL.md).
- Sanitization: There is no programmatic sanitization of ingested content before it is used to drive agent actions.
- [COMMAND_EXECUTION]: The skill is granted access to the Bash tool. Although the intended use is for file verification and publishing (SKILL.md), this capability could be exploited if malicious instructions are present in the ingested project data.
Audit Metadata