tessl-labs/skills-security-audit
Audit installed tessl skills for security risks and generate a formatted security report with per-skill risk levels and an overall project risk score
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 skill's SKILL.md Step 2 requires the agent to fetch and parse security pages from the public Tessl Registry (e.g., https://tessl.io/registry/... and https://tessl.io/registry/skills/github/...), using WebFetch to extract Snyk scores and findings that the agent then uses to form verdicts, so it clearly ingests untrusted third-party web content that could embed instructions or influence behavior.
Where we found it
tessl.io
domain · 5 sites
The plugin instructs the agent to use WebFetch to retrieve security pages from tessl.io registry at runtime, parse the content (Snyk scores, findings, verdicts), and incorporate it directly into the agent's security report, making it a vector for indirect prompt injection.
SKILL.md
48
https://tessl.io/registry/{workspace}/{tile}/security
SKILL.md
52
https://tessl.[REDACTED]
SKILL.md
57
https://tessl.io/registry/skills/github/{org}/{repo}/{skill-name}/security
SKILL.md
61
https://tessl.[REDACTED]
SKILL.md
66
Fetch each URL with WebFetch. Extract the Snyk score, verdict, and all finding details — category, description, and the specific reason it was flagged.
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
At runtime the skill explicitly uses WebFetch to retrieve registry pages like https://tessl.io/registry/{workspace}/{tile}/security and https://tessl.io/registry/skills/github/{org}/{repo}/{skill-name}/security and injects those fetched findings directly into the agent's report, so remote content can control the model's output.
Where we found it
https://tessl.io/registry/{workspace}/{tile}/security
url · 5 sites
The plugin instructs the agent to fetch remote registry pages at runtime via WebFetch and inject the retrieved content directly into its report output, making the remote content an unverifiable runtime dependency that controls the agent's behavior.
SKILL.md
48
https://tessl.io/registry/{workspace}/{tile}/security
SKILL.md
52
https://tessl.[REDACTED]
SKILL.md
57
https://tessl.io/registry/skills/github/{org}/{repo}/{skill-name}/security
SKILL.md
61
https://tessl.[REDACTED]
SKILL.md
66
Fetch each URL with WebFetch. Extract the Snyk score, verdict, and all finding details — category, description, and the specific reason it was flagged.
- Audited
- Security analysis