recall

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external memory files, creating a surface for potential instruction injection from stored data.
    1. Ingestion points: *.md files in the <repo-declared-memory-store> specified in SKILL.md.
    1. Boundary markers: The instructions for the subagent do not define delimiters to separate file content from the subagent's task.
    1. Capability inventory: The subagent is restricted to read-only file access and an explicit model tier as described in SKILL.md.
    1. Sanitization: Memory content is analyzed verbatim without sanitization.
  • [COMMAND_EXECUTION]: The skill provides a shell snippet for environment variable resolution and path normalization.
  • Evidence: SLUG=$(printf '%s' "$PWD" | sed 's#[/_.]#-#g') in SKILL.md. This is a benign path transformation operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 11:08 PM