slop-sense

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

• Third-party content exposure detected (low risk: 0.10). The workflow accepts text pasted by the user, read from local files, or fetched from user-provided URLs via curl/WebFetch without automatic monitoring of untrusted outsider submission feeds.

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

• Potentially malicious external URL detected (high risk: 0.70). The script score.sh executes npx -y -p slop-detector@1.2.0 slop-score which invokes an npm package registry download at runtime without an immutable hash digest, constituting a weak/unknown operational dependency.