retrospect-collab
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes historical session data, including 'user_prompts' and 'tool_calls', which could contain malicious instructions. * Ingestion points: Data is loaded from session logs using the 'retrospect-load-sessions.sh' script. * Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the analyzed content. * Capability inventory: The skill has access to 'Bash', 'Read', 'Write', and 'Grep' tools, enabling it to execute commands and modify files based on its analysis. * Sanitization: There is no evidence of sanitization or validation of the session data before processing.
- [COMMAND_EXECUTION]: The skill invokes a local Bash script ('retrospect-load-sessions.sh') from the plugin root to filter and load session paths, passing user-provided arguments ('$@') to the script.
Audit Metadata