Skills
Navigate
skills/qzaixh/zhiheng/dl-resume/Gen Agent Trust Hub

dl-resume

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md specify the execution of an auxiliary R&D script named resume to audit the Git root, configuration integrity, and workspace content fingerprints.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources which could theoretically contain untrusted instructions if the source files are compromised.
  • Ingestion points: SKILL.md indicates that the agent reads ../double-loop/references/runtime.md and interfaces with OpenWiki queues to determine state recovery.
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the ingested task protocols.
  • Capability inventory: The skill possesses the ability to interact with the local filesystem via Git operations (worktree, HEAD, fingerprints) and coordinate tasks between multiple agents.
  • Sanitization: The skill does not mention any validation, filtering, or sanitization steps for the data retrieved from runtime.md or the Wiki.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 05:45 AM