ketchup
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts on session history which may include data from untrusted external sources, such as tool outputs or web content retrieved earlier in the session. This creates a surface where malicious instructions hidden in that data could influence the agent's summary or the 'evidence links' it provides.
- Ingestion points: Processes all session messages and actions occurring since the user's last message in the
SKILL.mdinstructions. - Boundary markers: The skill does not define explicit delimiters or use 'ignore embedded instructions' warnings when processing the session history.
- Capability inventory: The skill focuses on text generation and does not explicitly request high-risk capabilities like file system writes or network access in its own instructions, though it operates within the agent's general context.
- Sanitization: There are no instructions to sanitize or validate the content of the action items or evidence links retrieved from the session history.
Audit Metadata