optise-helix-aeo-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data for analysis, which creates a potential surface for indirect prompt injection.
- Ingestion points: Section 4 of
SKILL.mdspecifies that the skill ingests tracking data in CSV or pasted table formats during 'Analysis mode'. - Boundary markers: There are no explicit instructions for the agent to utilize boundary markers or delimiters when processing the user-provided tracking data.
- Capability inventory: Section 0 of
SKILL.mdindicates that the agent has access toweb_searchandweb_fetchtools, which could be leveraged if malicious instructions were successfully injected through the data. - Sanitization: The instructions do not define any sanitization, validation, or escaping protocols for the content within the tracking data before it is analyzed.
Audit Metadata