managing-api-cache
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external API specifications from
{baseDir}/api-specs/to generate code and configure system components. - Ingestion points: API specifications are read from
{baseDir}/api-specs/as specified in the instructions ofSKILL.mdandreferences/implementation.md. - Boundary markers: The instructions do not define any delimiters or provide warnings to the agent to ignore instructions that might be embedded within the processed data files.
- Capability inventory: The skill allows the use of
Bash(api:cache-*),Write, andEdittools, which can be leveraged to execute commands or modify source code based on the potentially malicious input (as seen inSKILL.md). - Sanitization: There is no evidence of input validation, escaping, or sanitization of the content read from the API specifications before it is used in downstream tasks like code generation.
Audit Metadata