CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frb-fix-ci

Use when CI fails in flutter_rust_bridge - before deep investigation

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/frb-fix-ci/SKILL.md
SKILL.md
Quality
Evals
Security
Critical

E004: Prompt injection detected in skill instructions.

What this means

Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.

Why it was flagged

The skill is a legitimate CI-fix guide, but it tells the agent to run `git reset --hard HEAD && git clean -fdx` on a remote workspace by default, which can silently discard uncommitted work without confirmation, a possibly careless destructive step.

Report incorrect finding
Low

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 triage workflow reads CI check-runs, job logs, and PR state via `gh pr checks` and the check-runs API, and CI output for a PR is partly shaped by outsider-authored PR content (titles, commits, test output), which fits the "ANY GitHub PR reading" medium rule.

Low

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 skill references the `fzyzcjy/cargokit` repository, an individual-owned, unofficial source, as a submodule consumed by integrate-generated builds, and the instruction to push fixes there and update the submodule ref makes it a plausible build-time code dependency, so under the recall-first override it is rated medium despite no explicit fetch step.

Repository

fzyzcjy/flutter_rust_bridge

Path

.claude/skills/frb-fix-ci/SKILL.md

Audited
Security analysis
Snyk

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.