session-resume
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from an external file, which could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Contents are read from the
.claude/sessions/.current-sessionfile in SKILL.md.\n - Boundary markers: The skill does not implement delimiters or specific warnings to ignore instructions embedded within the session data.\n
- Capability inventory: The skill has minimal capabilities, limited to file reading and summarization; no network access, file writing, or command execution is requested.\n
- Sanitization: There is no evidence of sanitization or filtering applied to the data read from the session file.
Audit Metadata