knowledge-acquisition

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This skill contains multiple examples and flags that pass secrets on the command line or in headers (e.g., Authorization: Bearer , --password "MyPassword123!", and --api-key options), which would require the LLM to include secret values verbatim in generated commands or examples and therefore poses a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes ingesting outsider-authored web/Wikipedia/GitHub/PDF text (e.g., fetch_wikipedia.py and pdf2md.py outputs) into the wiki, which is then read back by the agent for LLM synthesis—so outsider free text can enter the LLM context indirectly via the wiki files it reads.