claude-historian
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from past sessions, establishing a vulnerability surface for indirect prompt injection if historical logs contain malicious instructions.\n
- Ingestion points: Historical data accessed via the
search()tool across various scopes includingconversations,errors, andmemories(SKILL.md).\n - Boundary markers: Absent; no delimiting instructions are provided to help the agent distinguish history from current instructions.\n
- Capability inventory: None; the skill consists of a markdown document with no associated scripts or tools.\n
- Sanitization: Absent; the guidelines do not specify any validation or filtering of the retrieved content.\n- [NO_CODE]: The skill consists exclusively of markdown documentation and does not contain any code, scripts, or external dependencies.
Audit Metadata