api-server-sent-events

Server-Sent Events (SSE / EventSource) exploitation — origin abuse for cross-site streaming exfil, prompt-injection via SSE messages into LLM clients, retry-after token leak, fragmenting events to bypass content-type sniffers.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/exploit/api/server-sent-events/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, actionable catalog of SSE attack vectors with executable examples, though it is reference-style rather than a sequenced testing workflow and a couple of bug classes lack concrete code.

Suggestions

Add concrete exploit commands or scripts for bug classes #4 and #5 to match the actionability of the others.

Reframe the body as a sequenced testing workflow (detect → enumerate bug classes → verify each → report) with explicit validation/check steps to raise workflow clarity.

Link the References entries (WHATWG, Detectify, simonw.net) to their URLs so they are directly navigable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete code and examples; the opening line explaining what SSE is ('SSE is one-way (server → browser) over HTTP/1.1 or HTTP/2...') is minor over-explanation of a concept Claude already knows and could be trimmed.	4 / 5
Actionability	Provides executable curl, HTML PoC, and Python sseclient snippets, but bug classes #4 (Retry timing DoS) and #5 (fragmenting past sniffers) are described without concrete exploit code or commands.	4 / 5
Workflow Clarity	Organized as a catalog (Detect → bug classes → Tooling → OPSEC) with a loose sequence but no explicit validation checkpoints or feedback loops; it reads as a reference rather than a sequenced testing workflow.	3 / 5
Progressive Disclosure	Well-organized into clear sections with no nested references, but the References section lists external resources by name without links and no bundle files exist to split deeper detail into.	4 / 5
	Total	15 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, naming four concrete SSE attack vectors, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger-term coverage is good though missing a couple of natural variations.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when testing SSE / text/event-stream endpoints, EventSource cross-origin abuse, or streaming LLM client prompt injection').

Include 'text/event-stream' and 'streaming' as natural trigger terms in the description to round out keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete attack actions — 'origin abuse for cross-site streaming exfil', 'prompt-injection via SSE messages into LLM clients', 'retry-after token leak', 'fragmenting events to bypass content-type sniffers' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly stated (SSE exploitation across named bug classes) but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural synonyms users would say ('Server-Sent Events', 'SSE', 'EventSource') but omits a few common natural terms like 'text/event-stream' and 'streaming' from the description field itself.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (SSE/EventSource exploitation) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/exploit/api/server-sent-events/SKILL.md
Commit: 0cf691e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.