brand-storytelling
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a 'Story Mining' pattern in
references/patterns.mdthat instructs the agent to process raw customer transcripts and support tickets. This creates an indirect prompt injection surface where malicious instructions embedded in external data could influence agent behavior. - Ingestion points: The
AI-Assisted Story Miningsection specifically targets external data sources like customer interviews, support tickets, and sales calls. - Boundary markers: The example prompt provided for story extraction lacks delimiters (such as XML tags or triple quotes) to separate the system instructions from the potentially untrusted transcript content.
- Capability inventory: While the skill itself is instructional, the AI agent environment typically provides file-system and network access capabilities that could be abused if an injection succeeds.
- Sanitization: There are no instructions for sanitizing, escaping, or filtering the external content before it is interpolated into the extraction prompt.
Audit Metadata