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

This skill's required workflow explicitly detects and ingests changed SKILL.md files from pull requests (e.g., "Detect changed SKILL.md files" and the various CI templates that run `tessl skill review --json <path>`), and it can optionally run `--optimize --yes` and commit optimized files back to the PR branch — meaning untrusted, user-generated repository/PR content is parsed and can directly influence automated tool actions and commits.

Where we found it

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 CI templates repeatedly run "npm install -g @tessl/cli" and then execute "tessl skill review" (and optionally "--optimize --yes"), meaning the workflow fetches and runs remote code from the Tessl npm package (e.g. https://www.npmjs.com/package/@tessl/cli), which is a required runtime dependency that can modify repo files.

Where we found it