detecting-aws-credential-exposure-with-trufflehog

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes explicit AWS access-key examples and shows CLI commands and a report format that embed and output key IDs (and tokens via $GITHUB_TOKEN), which requires the agent to handle and potentially emit credential values verbatim.

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the runtime scanning of public/third-party git content (e.g., trufflehog github --org=... / trufflehog git https://github.com/...), where TruffleHog ingests repository commit/file text authored by others and then emits it as JSON lines that the agent may pass into the LLM for analysis.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime installation command that fetches and executes a remote script via curl | sh (https://raw.githubusercontent.com/trufflesecurity/trufflehog/main/scripts/install.sh), which executes remote code during setup.