rev-symbol

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract and list string constants from decompiled code (shown in the output format as "Strings: "), which could include API keys, tokens, or passwords and therefore requires the LLM to output secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly tells the agent to perform web searches ("If uncertain, use Web Search to search: ...") to collect algorithm/magic-number/string matches from public websites, which clearly ingests untrusted third-party content that can influence naming and follow-up actions.