session-share
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell scripts and external tools (
agent-deck,jq,sed) to process session data. While it includes a check for session ID format inimport.sh, the use of shell variables like$SESSION_IDand$IMPORT_TITLEin command lines presents a risk if input validation is bypassed. - [INDIRECT_PROMPT_INJECTION]: The
import.shscript ingests untrusted session files created by other developers. These files contain conversation history that is directly written into the local Claude session storage (~/.claude/projects/). If a session file contains malicious instructions in themessagesarray, an agent resuming that session would execute them. - Ingestion points:
import.shreads from a user-provided JSON file path. - Boundary markers: None present. The content is directly converted to JSONL and placed in the session directory.
- Capability inventory: The skill uses
agent-deckto start and resume sessions, which has full access to the user's project and tools. - Sanitization: None performed during import. The
sanitize_jsonlfunction is only used during export to protect the exporter's data, not the importer's safety. - [DATA_EXFILTRATION]: While the skill claims to sanitize data,
export.shincludes a--no-sanitizeflag that allows exporting raw session data including credentials. Furthermore, the sanitization relies on regex patterns (sed) which may not capture all sensitive formats or obfuscated secrets.
Audit Metadata