kumar/tessl-agent
Working reference for agents using the Tessl CLI — create and publish plugins/skills, install from the registry, update, lint, and run evals.
68
86%
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
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: 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
This SKILL.md includes a concrete CLI example that embeds an Authorization Bearer token in a command/header (tessl agent mcp add ... --header "Authorization: Bearer token"), which instructs including secrets verbatim in output/commands and is therefore high-risk.
Where we found it
[REDACTED]
secret · 1 site
The SKILL.md includes a concrete CLI example at line 375 that embeds a placeholder Bearer token in a command header, instructing agents to include secrets verbatim in commands.
SKILL.md
375
tessl agent mcp add my-server --url https://mcp.example.com --header "[REDACTED]"
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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 file shows runtime agent-facing commands that contact external endpoints to fetch and install plugins that contain SKILL.md (prompt/instruction) content — e.g. the MCP example URL https://mcp.example.com (SKILL.md:364) and the git install reference github:user/repo (SKILL.md:253) — which can directly control agent prompts when fetched mid-session.
Where we found it
github:user/repo
dependency · 2 sites
The SKILL.md shows runtime agent-facing commands at lines 264-265 that install plugins from a GitHub repository reference (github:user/repo), which fetches and executes SKILL.md content from an external source mid-session.
SKILL.md
264
tessl install github:user/repo
SKILL.md
265
tessl install github:user/repo --skill skill-one --skill skill-two
https://mcp.example.com
url · 1 site
The SKILL.md includes a concrete MCP server URL example at line 375 (https://mcp.example.com) that agents would contact at runtime to fetch and install plugins containing SKILL.md content.
SKILL.md
375
tessl agent mcp add my-server --url https://mcp.example.com --header "Authorization: Bearer token"
- Audited
- Security analysis