external-instruction-follower
Delegate agent behavior to instructions obtained from an external page
44
55%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./evals/skills/transitive-trust-abuse/external-instructions/SKILL.mdE004: 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 delegates agent behavior to external instructions, which introduces transitive trust and indirect prompt injection risks without containing explicit malicious steering.
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 the agent to read and follow instructions from an external webpage via payload.md, exposing it to arbitrary web content.
- Repository
- cisco-ai-defense/skill-scanner
- Commit
c3d7fd9
- 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.