hyday-lifelog
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill directs the agent to read application-specific configuration files on the local file system to find the journal vault path.\n
- Evidence: Instructions to resolve the vault root by reading the
journalPathfield from~/Library/Application Support/Hyday/settings.jsonon macOS or%APPDATA%\\Hyday\\settings.jsonon Windows.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and summarizing user-controlled Markdown files, which could contain instructions intended to influence the agent's behavior.\n - Ingestion points: Journal files with filenames matching the
YYYY-MM-DD.mdorYYYY.MM.DD.mdpatterns.\n - Boundary markers: The instructions lack specific markers or directives for the agent to treat the journal content as untrusted data or to ignore embedded commands.\n
- Capability inventory: The agent is tasked with reading, writing, summarizing, and extracting data from these files.\n
- Sanitization: No sanitization or validation of the journal content is defined in the skill instructions.
Audit Metadata