discover-journey-map
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data, such as customer interview transcripts, survey results, and support tickets, to synthesize journey maps. This creates an attack surface where malicious instructions hidden in the research data could attempt to influence the agent's behavior during the synthesis process.
- Ingestion points: Research data inputs specified in
SKILL.md(interview synthesis, survey results, support tickets, and analytics). - Boundary markers: The skill output is structured into specific markdown sections and tables defined in
references/TEMPLATE.md, which helps maintain output structure but does not fully isolate the model from embedded instructions. - Capability inventory: The skill utilizes
ReadandGreptools to access and search through data sources. - Sanitization: No explicit sanitization or instructions to ignore instructions embedded within the research data are present in the core instructions.
Audit Metadata