The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a local command-line interface tool (ae-cli) to fetch workspace data and append reports.
Evidence: The instructions explicitly direct the agent to run commands such as ae-cli things +digest for data collection and ae-cli things entry append for writing report data back to the system.
[INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external workspace items (tasks, progress logs, entries) to generate summaries.
Ingestion points: The agent ingests untrusted data from the output of ae-cli things +digest and +detail as described in SKILL.md.
Boundary markers: There are no explicit instructions for the agent to use delimiters (like XML tags or triple quotes) when processing retrieved task descriptions or to ignore potential instructions embedded within those tasks.
Capability inventory: The agent has the capability to write data back to the workspace using ae-cli things entry append as noted in the 'Output and Write Back' section of SKILL.md.
Sanitization: No specific sanitization or filtering logic is prescribed for the data retrieved from external workspace items before it is used to generate reports or written back to the system.

ae-things-progress