skills/edheltzel/recall/recall-dump/Gen Agent Trust Hub

recall-dump

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a non-standard command-line tool 'recall', likely specific to the author, to perform database operations and persist conversation history.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where user-supplied content is interpolated into a shell command.
  • Ingestion points: The user-provided title argument defined in 'SKILL.md'.
  • Boundary markers: The command template 'recall dump ""' uses double quotes which can be bypassed by shell metacharacters like backticks or semicolons.
  • Capability inventory: The skill requires the ability to execute shell commands to interact with the 'recall' tool and the optional 'fabric' extraction utility.
  • Sanitization: The instructions do not specify any sanitization or validation for the user-provided title before it is passed to the shell command.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 02:19 AM