inno-code-survey
Acquires missing code repositories for the selected idea (Phase A) and conducts comprehensive code survey mapping academic concepts to implementations (Phase B). Outputs acquired_code_repos, updated_prepare_res, and model_survey for downstream use by inno-implementation-plan.
55
62%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/inno-code-survey/SKILL.mdLow
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
In Phase B, the Code Survey Agent builds and sends a first prompt containing free text fields (`survey_res`/`selected_idea`) and then reads/uses local files and repo contents under `Experiment/code_references/` (including `README.md` and source files) which originate from outsider-authored GitHub repositories that Phase A can fetch based on earlier gaps.
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 performs runtime GitHub API calls (e.g., https://api.github.com/search/repositories and the example request https://api.github.com/search/repositories?q=sinkhorn+attention&per_page=5) and then clones remote repositories (e.g., https://github.com/user/repo.git) which fetches external code that is injected into the agent's context and used to build prompts/reports, so these external URLs are used at runtime to supply content that directly controls the agent's behavior.
- Repository
- OpenLAIR/dr-claw
- Commit
6da7f7c
- 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.