wait-what
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process information from
CONTEXT.mdandCONTEXT-MAP.md. This creates a surface where instructions embedded in those files could influence agent behavior. - Ingestion points: Processes content from
CONTEXT.mdandCONTEXT-MAP.mdas instructed inSKILL.md. - Boundary markers: Absent. The instructions do not specify delimiters or guidelines to ignore potential instructions within the context files.
- Capability inventory: None. The skill has
disable-model-invocation: trueset in the frontmatter, which restricts the agent from using tools or performing actions beyond text generation. - Sanitization: Absent. There is no logic to filter or validate the content retrieved from the context files.
Audit Metadata