easysdd-issue-analyze

Warn

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python utility using shell interpolation of variables derived from issue metadata.\n
  • Evidence: The command python easysdd/tools/search-yaml.py --dir easysdd/compound --query "{issue 关键词}" in SKILL.md directly interpolates keywords into a shell execution string.\n
  • Risk: Maliciously crafted keywords containing shell metacharacters could allow execution of arbitrary code.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from issue reports and codebases, creating an attack surface for indirect prompt injection.\n
  • Ingestion points: Reads {slug}-report.md and various project source files.\n
  • Boundary markers: Absent; there are no specific instructions or delimiters used to prevent the agent from following instructions embedded within the analyzed data.\n
  • Capability inventory: Includes file system enumeration (grep/glob), file reading/writing, and execution of local scripts.\n
  • Sanitization: Absent; the skill does not specify any validation or filtering of the content it processes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 19, 2026, 02:38 PM