readback
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML configuration. It does not contain any scripts, executables, or third-party dependencies in
SKILL.mdoragents/openai.yaml. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and restate user requests, which creates a data ingestion surface.
- Ingestion points: User requests are ingested from the conversation context as specified in
SKILL.md. - Boundary markers (absent): There are no specific delimiters or instructions to ignore embedded commands within the user request.
- Capability inventory: The skill has no capabilities; tool invocation is explicitly disabled via the
disable-model-invocation: truesetting in theSKILL.mdfrontmatter. - Sanitization (absent): The skill does not perform any escaping, validation, or filtering of the user's input before restating it.
Audit Metadata