The Agent Skills Directory

[SAFE]: The skill operates using a set of purpose-built tools (wiki_search, wiki_read_page, wiki_read_source) and restricts write operations to a single log file (wiki/log.md). The workflow is strictly defined as an audit process rather than an automated modification process.- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because its core function involves reading and processing untrusted data from wiki pages and raw sources. Malicious content within these files could attempt to manipulate the agent's summary or the content of the log entries. However, this is an inherent risk of the skill's primary purpose and is mitigated by the restricted write access.
Ingestion points: Content is ingested via the wiki_read_page and wiki_read_source tools within the workflow.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers for the processed data.
Capability inventory: The skill has access to wiki_write_page (restricted by instructions to wiki/log.md) and search/read tools.
Sanitization: No specific content sanitization or validation routines are described for the ingested text.

wiki-lint