asc-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill delegates to public package/repo commands (e.g., "npx --yes skills add tddworks/asc-cli-skills", "npx skills check/update") to fetch and install skill SKILL.md files into ~/.claude/skills and the agent parses those SKILL.md affordances (e.g., install/uninstall commands), so untrusted repository content from the public tddworks/asc-cli-skills repo can directly influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runtime calls npx (e.g., "npx --yes skills add tddworks/asc-cli-skills" / "npx skills add tddworks/asc-cli-skills --list"), which fetches and executes remote package content from the tddworks/asc-cli-skills repository and installs SKILL.md files that directly define agent prompts/affordances, so this external repository is a runtime dependency that can control prompts and execute code.