luci-profile
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated content from daily reports and meeting write-ups to create a profile summary, which creates a potential surface for indirect prompt injection if the source documents contain malicious instructions.
- Ingestion points: Daily files, meeting write-ups, and entity definitions located in the
~/.Life/directory. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potential commands embedded within the source notes.
- Capability inventory: The skill allows the agent to read local files and write/overwrite
~/.Life/profile.mdand history files in~/.Life/profile/history/. - Sanitization: No explicit sanitization or instruction-filtering is applied to the content extracted from notes before it is formatted into the profile.
Audit Metadata