multica-skill-importing
Use when asked to import or install a specific skill into this Multica workspace from a URL or slug. Not for choosing which skill the user needs; never treat a local installer such as `npx skills add` as the final install.
69
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Skill import/refresh fetches and ingests outsider-authored free text from the externally provided skill URL (or uploaded archive) via the Multica skill import endpoints POST /api/skills/import and POST /api/skills/{id}/refresh, where the downloaded SKILL.md and supporting files are parsed and stored.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The import flow downloads skill bundles from external hosts (e.g., "github.com/owner/repo" and "https://skills.sh/acme/repo/review-helper") at import/refresh time and uses the fetched SKILL.md/supporting files as the skill content that controls agent prompts/behavior, so these URLs are runtime dependencies that can directly control agent instructions.
- Repository
- multica-ai/multica
- Commit
11ab949
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.