The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes user-generated messages and articles from the public Atlassian Community forum. This external content is authored by third-party users and could potentially contain hidden instructions designed to influence the agent's behavior.
Ingestion points: Untrusted data enters the agent context via the Atlassian Community API endpoint using curl commands defined in SKILL.md.
Boundary markers: The instructions do not specify the use of clear delimiters or guardrails to separate the fetched community content from the agent's internal instructions.
Capability inventory: The skill uses curl and jq within the agent shell to perform network operations and process data.
Sanitization: The skill includes instructions to escape single quotes in LiQL queries to prevent syntax errors, but does not provide mechanisms for sanitizing the actual content of the retrieved forum posts before synthesis.
[COMMAND_EXECUTION]: The skill executes shell commands to interact with the Atlassian Community API.
Evidence: SKILL.md provides a bash snippet using curl and jq to query the https://community.atlassian.com/forums/s/api/2.0/search endpoint. This is consistent with the skill's primary function of researching forum posts.

atlassian-community-search