ae-things-review
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a workspace, including item titles, descriptions, and progress records, via the
ae-clitool, creating a surface for potential indirect prompt injection attacks.\n - Ingestion points: The skill instructions in
SKILL.mdspecify reading workspace data throughae-cli things +detailandae-cli things +digestcommands.\n - Boundary markers: The skill does not define explicit delimiters to isolate external workspace content from its instructional context, though it does mandate verifying data consistency markers such as
consistencyandcollectedAt.\n - Capability inventory: The skill is capable of reading and, upon explicit user request, modifying workspace items via the
ae-clitool.\n - Sanitization: There is no evidence of data sanitization or escaping for the ingested content before it is processed by the agent.
Audit Metadata