The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from external Confluence documentation, which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: The skill uses search, fetch, and getConfluencePage to retrieve content from external Atlassian sites as specified in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions embedded within the retrieved documentation.
Capability inventory: The skill possesses write capabilities, including createConfluencePage and updateConfluencePage, which could be exploited if the agent obeys instructions found in read content.
Sanitization: There is no evidence of filtering or sanitization of the content retrieved from Confluence pages before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill interacts with Atlassian Cloud infrastructure to perform its primary tasks.
Fetches data from and sends updates to Confluence site URLs (e.g., atlassian.net) based on user-provided Cloud IDs or site addresses.

confluence-assistant