btca-local
Invoke this skill when the user says "use btca"
38
35%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/btca-local/SKILL.mdW007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs the agent to clone/load repos and "include very clear and complete code snippets" from them, which will cause the model to output repository contents verbatim (potentially including API keys/secrets present in those files).
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 workflow instructs cloning/updating git repos (and/or “load and reference” user-supplied GitHub repo links) at runtime, so the LLM context can ingest outsider-authored free text from those fetched repositories (e.g., README/source/docs) via the “load”/“search” steps.
- Repository
- stickerdaniel/linkedin-mcp-server
- Commit
f4fc67d
- 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.