tessl-academy/tessl-change-review-walkthrough
Guided walkthrough for the Reviewing your changes with tessl change review lesson: run a change review over a real diff with a code-review skill, read the summary, inline hunk comments, and unplaced findings, and see how the structured output feeds a GitHub review.
75
94%
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
The required runtime workflow invokes `tessl change review`, which “pulls one from the registry” and then runs a model to generate review text; this implies the agent/CLI will ingest outsider-authored content (the selected reviewer skill from a public registry and/or the diff content from the learner’s repo) into the LLM context, creating an indirect prompt-injection surface.
Where we found it
learner's git diff content
content-type · 4 sites
The tessl change review command ingests the learner's git diff into an LLM for review, which is outsider-authored content relative to the plugin.
SKILL.md
40
tessl change review --skill tessl/code-review#review-code-legibility --base origin/main
SKILL.md
62
tessl change review --skill tessl/code-review#review-code-legibility --json
SKILL.md
63
tessl change review --skill tessl/code-review#review-code-legibility --output review.json
SKILL.md
74
tessl change review --skill tessl/code-review#review-code-legibility
registry-hosted reviewer skill content
content-type · 5 sites
The tessl CLI fetches a reviewer skill from a public registry at runtime, and its content (prompts/instructions) is ingested into the LLM context, creating an indirect prompt-injection surface via the registry-hosted skill.
SKILL.md
31
the command pulls one from the registry
SKILL.md
40
tessl change review --skill tessl/code-review#review-code-legibility --base origin/main
SKILL.md
62
tessl change review --skill tessl/code-review#review-code-legibility --json
SKILL.md
63
tessl change review --skill tessl/code-review#review-code-legibility --output review.json
SKILL.md
74
tessl change review --skill tessl/code-review#review-code-legibility
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 tessl CLI explicitly "pulls one from the registry" and the lesson runs `tessl change review --skill tessl/code-review#review-code-legibility`, so the reviewer skill (tessl/code-review#review-code-legibility) is fetched at runtime and can provide external prompts/instructions that control the review execution.
Where we found it
tessl/code-review#review-code-legibility
dependency · 4 sites
The reviewer skill tessl/code-review#review-code-legibility is fetched at runtime from a public registry by the tessl CLI and provides external prompts/instructions that control the review execution.
SKILL.md
40
tessl change review --skill tessl/code-review#review-code-legibility --base origin/main
SKILL.md
62
tessl change review --skill tessl/code-review#review-code-legibility --json
SKILL.md
63
tessl change review --skill tessl/code-review#review-code-legibility --output review.json
SKILL.md
74
tessl change review --skill tessl/code-review#review-code-legibility
- Audited
- Security analysis