forge
Reference-grounded prompt-artifact formation. Reads a target reference doc, surfaces the under-determined contract coordinates, and projects a ready-to-use prompt or standing skill recipe.
48
51%
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 ./epistemic-cooperative/skills/forge/SKILL.mdW011: 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 `higgsfield` adapter fetches web pages dynamically via search and extraction (`fetch_guide_snapshot`) from `higgsfield.ai` URLs to acquire prompt guides.
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 contains instructions for dynamic web fetches from third-party vendor URLs (`https://platform.claude.com/docs/en/...`, `https://developers.openai.com/...`, `https://higgsfield.ai/...`) to acquire runtime guide snapshots and prompt schemas that govern the skill's behavior, placing it under common/reputable unofficial or weak external dependencies.
- Repository
- jongwony/epistemic-protocols
- Commit
3ffe94c
- 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.