generating-api-docs
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external API specification files from the
{baseDir}/api-specs/directory, creating a risk for indirect prompt injection. Malicious instructions within these specs could manipulate the agent. - Ingestion points: Files in
{baseDir}/api-specs/read by theReadtool. - Boundary markers: None; the skill lacks delimiters or instructions to ignore embedded directives.
- Capability inventory: Includes
Write,Edit, andBash(api:docs-*)tools. - Sanitization: No validation or sanitization of spec content is defined.
- [COMMAND_EXECUTION]: The skill uses a restricted shell tool
Bash(api:docs-*)for scaffolding. While restricted by a prefix, it is an execution surface that could be exploited via injection.
Audit Metadata